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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6772
    Prev
    Next
    INDEX
    Explanations

    the word "require" and sometimes related code functions

    oai_token-act-pair · gemini-2.0-flash

    require

    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
     itſelf
    -0.91
     Jefus
    -0.82
    esModule
    -0.77
     edn
    -0.73
     $_"
    -0.73
    ContentAsync
    -0.71
     theſe
    -0.71
     Answered
    -0.71
    GEBURTS
    -0.69
     chofe
    -0.69
    POSITIVE LOGITS
    <blockquote>
    0.62
     समीक्षक
    0.60
     calcetines
    0.60
    žev
    0.56
     milliers
    0.56
    tuig
    0.54
    heide
    0.54
    ocrine
    0.54
    ่
    0.53
     Schroeder
    0.53
    Activations Density 0.635%

    No Known Activations