© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14425
    Prev
    Next
    INDEX
    Explanations

    words related to technical processes involving file management, probability calculations, scientific investigations, or javascript programming

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks indicating excitement or surprise

    np_token-act-pair-logits · gpt-4o-mini

    end punctuation

    np_max-act-logits · gemini-2.0-flash

    records

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.73
    complexContent
    -0.73
     незавершена
    -0.73
    NUMX
    -0.71
     HasFactory
    -0.68
    complexType
    -0.67
    queryInterface
    -0.66
     @"/
    -0.64
    CppMethod
    -0.63
     createState
    -0.63
    POSITIVE LOGITS
    !
    0.79
    ?
    0.78
    !,
    0.71
    !”
    0.62
    !!!
    0.60
    ！
    0.60
    !!
    0.59
    !),
    0.58
    !}
    0.56
    ？
    0.56
    Activations Density 22.162%

    No Known Activations