© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5661
    Prev
    Next
    INDEX
    Explanations

    common words that appear frequently, such as "the," "a," and "and," alongside words associated with film or television reviews and/or with characters in film or television

    oai_token-act-pair · gemini-2.0-flash

    terms related to storytelling and character development

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

    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_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
    SequentialGroup
    -0.54
    PerformLayout
    -0.52
    InjectAttribute
    -0.52
    ftagPool
    -0.49
    الحياه
    -0.47
    ScopeManager
    -0.46
     समीक्षाओं
    -0.45
    الإنجليزية
    -0.44
    getColumnIndex
    -0.44
    invokeLater
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.73
     Ceinture
    0.72
    demort
    0.63
     author
    0.63
     Cushing
    0.61
    ghijklmnop
    0.60
     plot
    0.60
    frain
    0.59
     Италијани
    0.58
     visualization
    0.58
    Activations Density 1.833%

    No Known Activations