© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11881
    Prev
    Next
    INDEX
    Explanations

    code syntax and copyright-related tokens.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -2.50
    The
    -0.81
    '
    -0.79
    ’
    -0.75
     the
    -0.66
    ↵
    -0.62
    This
    -0.61
    There
    -0.57
    It
    -0.56
    With
    -0.54
    POSITIVE LOGITS
     NSCoder
    0.69
    InputBorder
    0.69
     resourceCulture
    0.69
    ollectionView
    0.68
     "..\..\
    0.66
     numerus
    0.66
    IMON
    0.66
    AutoScaleMode
    0.64
     مشين
    0.64
     exceptions
    0.63
    Activations Density 0.170%

    No Known Activations