© 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. 14744
    Prev
    Next
    INDEX
    Explanations

    a variety of numerical data related to laboratory results, economics, and percentages.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     للاسماء
    -0.88
    RenderAtEndOf
    -0.83
     autorytatywna
    -0.82
     EconPapers
    -0.82
     Theſe
    -0.79
     мәкал
    -0.79
     виправивши
    -0.79
    ValueStyle
    -0.78
     Мексичка
    -0.77
    UnusedPrivate
    -0.77
    POSITIVE LOGITS
     tanul
    0.11
    <unused61>
    0.10
    <unused63>
    0.10
     yks
    0.09
     getById
    0.09
     lehet
    0.08
    <unused62>
    0.07
     vezet
    0.07
    ‍
    0.07
     által
    0.06
    Activations Density 22.283%

    No Known Activations