© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4473
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially those used in graphics and web development

    oai_token-act-pair · gemini-2.0-flash

    say "=" and "-"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ,
    -0.77
    <eos>
    -0.68
     (
    -0.65
    ↵
    -0.65
    ↵↵
    -0.64
    can
    -0.57
     
    -0.57
    .
    -0.57
    ta
    -0.56
    1
    -0.53
    POSITIVE LOGITS
    ItemBackground
    0.97
     समीक्षाओं
    0.95
    ſelves
    0.92
    Portale
    0.90
     autorytatywna
    0.90
     consultato
    0.88
     Monfieur
    0.86
    rungsseite
    0.84
     للمعارف
    0.84
    usermodel
    0.84
    Activations Density 1.596%

    No Known Activations