© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12102
    Prev
    Next
    INDEX
    Explanations

    the number 1

    oai_token-act-pair · gemini-2.0-flash

    The numeral one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     that
    -0.39
     fVar
    -0.33
     Cassel
    -0.33
    The
    -0.33
     in
    -0.32
    Carlos
    -0.32
    That
    -0.31
     <<=
    -0.31
    Passcode
    -0.30
     like
    -0.30
    POSITIVE LOGITS
     كومونز
    0.81
     '{@
    0.77
    contentLoaded
    0.76
    kháu
    0.72
    MIDDLEWARE
    0.71
     Drapeau
    0.71
     getItemId
    0.70
    出版年
    0.69
    complexContent
    0.68
     OFDb
    0.68
    Activations Density 2.213%

    No Known Activations