© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5332
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly Java or C-like syntax, often involving mathematical calculations or coordinate systems

    oai_token-act-pair · gemini-2.0-flash

    Integer declaration

    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
     /\.(
    -0.77
    Dziękuję
    -0.74
     itſelf
    -0.72
     againſt
    -0.68
     morire
    -0.68
    ]='\
    -0.67
     typelib
    -0.66
     myſelf
    -0.66
     通販
    -0.65
    GIVEREF
    -0.65
    POSITIVE LOGITS
     int
    1.11
    int
    1.08
     Int
    0.75
    Int
    0.73
    round
    0.63
     round
    0.57
    toInt
    0.56
    intValue
    0.56
    Round
    0.54
    INT
    0.51
    Activations Density 1.070%

    No Known Activations