© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8792
    Prev
    Next
    INDEX
    Explanations

    code syntax such as parentheses, colons, and brackets

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     the
    -1.23
     to
    -1.22
     for
    -1.18
     that
    -1.13
     in
    -1.11
     from
    -1.05
     with
    -1.03
     as
    -1.00
     of
    -0.99
     or
    -0.98
    POSITIVE LOGITS
     Shakspeare
    0.81
     Jefus
    0.75
     Theſe
    0.73
     ſche
    0.73
     itſelf
    0.73
     @"";
    0.71
     Shaksp
    0.70
     purpoſe
    0.68
     anún
    0.67
     '-';
    0.67
    Activations Density 3.408%

    No Known Activations