© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4109
    Prev
    Next
    INDEX
    Explanations

    the occurence of the word division, and perhaps time-related words

    oai_token-act-pair · gemini-2.0-flash

    division

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -1.27
     it
    -1.23
     a
    -1.13
     for
    -1.11
     and
    -1.05
     in
    -1.03
     to
    -1.02
     is
    -0.95
     so
    -0.93
     (
    -0.93
    POSITIVE LOGITS
     Theſe
    2.19
     Monfieur
    2.06
     myſelf
    2.00
     itſelf
    1.91
     Jefus
    1.88
     Efq
    1.83
     Shakspeare
    1.80
     ſeveral
    1.77
     Anſ
    1.77
     Reſ
    1.72
    Activations Density 1.785%

    No Known Activations