© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16047
    Prev
    Next
    INDEX
    Explanations

    text related to scientific publications or data analysis, especially section headers, references, and formatting elements

    oai_token-act-pair · gemini-2.0-flash

    periods

    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
     implementation
    -0.68
     it
    -0.57
     evaluation
    -0.57
     environment
    -0.56
     overview
    -0.54
    aspetto
    -0.54
    recent
    -0.53
     methodological
    -0.52
     inference
    -0.52
     current
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.68
    UnusedPrivate
    0.66
     JpaRepository
    0.64
    ContentAlignment
    0.63
    TypedDataSet
    0.61
    Aiheesta
    0.58
    HtmlAttribute
    0.57
    SharedDtor
    0.57
    balleur
    0.57
    featureID
    0.56
    Activations Density 10.117%

    No Known Activations