Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7717
    Prev
    Next
    INDEX
    Explanations

    code snippets including copyright notices, years, and code-related terminology

    oai_token-act-pair · gemini-2.0-flash

    2

    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
    featureID
    -0.67
    twimg
    -0.67
    WithMany
    -0.64
    istoitu
    -0.63
    DoubleQuotes
    -0.62
     numerus
    -0.58
     JsonResult
    -0.56
     PopupWindow
    -0.56
    üyada
    -0.56
    tagHelperRunner
    -0.56
    POSITIVE LOGITS
    <bos>
    1.37
    '
    0.83
     ſte
    0.67
    ↵↵
    0.63
     Jefus
    0.62
    ſelf
    0.61
    ’
    0.60
     purpoſe
    0.60
    //
    0.57
     Inscrivez
    0.56
    Activations Density 1.796%

    No Known Activations