© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8081
    Prev
    Next
    INDEX
    Explanations

    citations of academic papers

    oai_token-act-pair · gemini-2.0-flash

    commas and parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ,
    -0.44
    roid
    -0.41
    over
    -0.37
    TRAILING
    -0.36
     mis
    -0.36
    j
    -0.36
    /
    -0.36
     rup
    -0.36
    mp
    -0.35
     lat
    -0.35
    POSITIVE LOGITS
    InitVars
    0.81
    EndInit
    0.77
    AnimationsModule
    0.74
    __':
    0.71
    gonic
    0.69
    [])
    0.69
     كومونز
    0.69
     doInBackground
    0.68
    HasForeignKey
    0.68
    </thead>
    0.68
    Activations Density 2.893%

    No Known Activations