© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6100
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ENNE
    -0.50
     a
    -0.48
    rungsseite
    -0.48
     tengah
    -0.46
    OPHY
    -0.45
    tory
    -0.45
    erweise
    -0.45
    mson
    -0.44
     .=
    -0.43
     Back
    -0.43
    POSITIVE LOGITS
     Мексичка
    0.85
    HtmlAttribute
    0.78
    цездатний
    0.75
    expandindo
    0.73
     للاسماء
    0.69
    EndInit
    0.67
    ագրություններ
    0.65
     Winaray
    0.65
     Dummies
    0.65
    endphp
    0.64
    Activations Density 0.457%

    No Known Activations