© 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. 13677
    Prev
    Next
    INDEX
    Explanations

    words in mathematical proofs

    oai_token-act-pair · gemini-2.0-flash

    abstract or technical phrases

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

    Technical/math documents

    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
    pró
    -0.48
    stęp
    -0.47
     pescoço
    -0.46
     Prüf
    -0.46
     devenir
    -0.44
     whipping
    -0.44
     gardent
    -0.44
    prototype
    -0.44
     Burr
    -0.44
     protège
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.79
    ########.
    0.79
    MessageOf
    0.76
     esternos
    0.73
    Vidite
    0.73
    +#+#
    0.73
    enumi
    0.72
    mybatisplus
    0.70
    AnimationsModule
    0.70
    Initializable
    0.68
    Activations Density 3.127%

    No Known Activations