© 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. 12815
    Prev
    Next
    INDEX
    Explanations

    the word "bind" in technical documentation and code samples

    oai_token-act-pair · gemini-2.0-flash

    bind

    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
    ,
    -1.09
     in
    -1.03
     for
    -0.83
     I
    -0.80
    '
    -0.79
     is
    -0.79
     da
    -0.79
     was
    -0.78
     on
    -0.75
     than
    -0.75
    POSITIVE LOGITS
     Efq
    1.95
     Monfieur
    1.94
     Diſ
    1.91
     Jefus
    1.88
     Majefty
    1.86
     ſeveral
    1.84
     itſelf
    1.77
     becauſe
    1.75
     himſelf
    1.73
     Houſe
    1.73
    Activations Density 1.550%

    No Known Activations