© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6819
    Prev
    Next
    INDEX
    Explanations

    code snippets and configuration elements, possibly from different programming languages

    oai_token-act-pair · gemini-2.0-flash

    Azure Container Registry code

    np_max-act-logits · 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
     aporte
    -0.49
     demurrer
    -0.48
    InvalidProtocol
    -0.48
     ẞ
    -0.48
     Cauchy
    -0.46
    XtraEditors
    -0.46
     fullname
    -0.45
     getF
    -0.45
     $=$
    -0.45
     mCurrent
    -0.45
    POSITIVE LOGITS
     as
    1.25
     for
    1.13
     in
    1.07
     when
    1.05
     from
    1.01
     with
    1.01
     if
    1.00
     to
    0.98
     because
    0.95
     after
    0.93
    Activations Density 10.415%

    No Known Activations