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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4535
    Prev
    Next
    INDEX
    Explanations

    statistical analysis results including confidence intervals, p values, and odds ratios

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     JScrollPane
    -0.43
    ToJson
    -0.41
    vänt
    -0.40
    dafx
    -0.40
     japones
    -0.39
     Handles
    -0.38
    </thead>
    -0.38
     Anfang
    -0.38
    minify
    -0.38
    介意
    -0.38
    POSITIVE LOGITS
    хьтан
    0.82
    parsedMessage
    0.81
     rhestr
    0.73
     يتيمه
    0.69
    ArrowToggle
    0.68
     insuffisamment
    0.67
    mybatisplus
    0.66
    日閲覧
    0.66
    GraphicsUnit
    0.66
    énario
    0.66
    Activations Density 31.354%

    No Known Activations