© 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. 13842
    Prev
    Next
    INDEX
    Explanations

    code, Samoan words, or the letters AN or FA

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'fa' or related code elements

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

    code and programming

    np_max-act-logits · gemini-2.0-flash
    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
     EClass
    -0.40
     puns
    -0.39
     translational
    -0.39
     diurnal
    -0.38
    Rüyada
    -0.36
     disjoint
    -0.36
    rativa
    -0.35
    法律
    -0.35
     fermions
    -0.35
     pronounced
    -0.35
    POSITIVE LOGITS
     مشين
    0.88
    __':
    0.76
    +#+#
    0.70
     CreateTagHelper
    0.69
    InjectAttribute
    0.68
    __":
    0.67
     createSprite
    0.67
     dAtA
    0.67
    RunWith
    0.66
    Бахар
    0.64
    Activations Density 0.036%

    No Known Activations