© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6366
    Prev
    Next
    INDEX
    Explanations

    fragments of sentences and questions, especially those using french words (but not exclusively)

    oai_token-act-pair · gemini-2.0-flash

    words related to questions or inquiries

    np_token-act-pair-logits · gpt-4o-mini

    French language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ItemBackground
    -0.50
     useCallback
    -0.50
    DispatchToProps
    -0.45
     recorders
    -0.43
    agisse
    -0.41
    PerformLayout
    -0.39
    ագրություններ
    -0.38
    local
    -0.37
    ядок
    -0.37
    ::__
    -0.37
    POSITIVE LOGITS
    PMailer
    0.84
    MessageOf
    0.76
    AnchorStyles
    0.68
     GenerationType
    0.65
     there
    0.64
    there
    0.63
     ehemaligen
    0.62
    theres
    0.61
    Theres
    0.60
    antaranya
    0.59
    Activations Density 1.087%

    No Known Activations