© 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. 5979
    Prev
    Next
    INDEX
    Explanations

    articles and determiners (the, a, an, this) preceding words related to movies, performances or acts.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    :✨
    -0.71
    脚注の使い方
    -0.60
    piram
    -0.57
    parsedMessage
    -0.56
     Characters
    -0.56
    DeleteBehavior
    -0.55
     MainAxisSize
    -0.55
    Lähteet
    -0.55
    DockStyle
    -0.54
    EndGlobalSection
    -0.53
    POSITIVE LOGITS
    [::-
    0.49
    навли
    0.49
    ectl
    0.48
    grun
    0.48
    цуз
    0.46
    หมือน
    0.45
     ویکی‌پدیای
    0.45
    EndContext
    0.45
     apes
    0.45
    OnItem
    0.44
    Activations Density 5.420%

    No Known Activations