© 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. 10758
    Prev
    Next
    INDEX
    Explanations

    commas and the word "import," as well as other seemingly random words.

    oai_token-act-pair · gemini-2.0-flash

    import

    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
     westward
    -0.56
     meninos
    -0.54
     vegetative
    -0.54
     mė
    -0.53
     carnal
    -0.53
     euth
    -0.52
     eastward
    -0.52
     biotic
    -0.51
     geological
    -0.51
     latest
    -0.49
    POSITIVE LOGITS
    bootstrapcdn
    0.73
    المشاركات
    0.70
     have
    0.66
    PreInfinity
    0.66
    كويكب
    0.66
    بوابة
    0.64
    NameInMap
    0.64
     wireType
    0.63
     protoimpl
    0.61
     see
    0.60
    Activations Density 2.399%

    No Known Activations