© 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. 6316
    Prev
    Next
    INDEX
    Explanations

    words related to government proceedings, especially elections and meetings

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'special'

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

    special

    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
    SourceChecksum
    -0.74
    TypedDataSet
    -0.70
     ویکی‌پدی
    -0.69
     Infórmanos
    -0.69
     autorytatywna
    -0.69
    RenderAtEndOf
    -0.68
    VIAF
    -0.68
     '\\;'
    -0.68
    出版年
    -0.66
    InputTagHelper
    -0.65
    POSITIVE LOGITS
     special
    0.83
     Special
    0.82
    Special
    0.75
    special
    0.70
     general
    0.63
     Spezial
    0.62
     SPECIAL
    0.61
    SPECIAL
    0.59
    特殊
    0.57
     spesial
    0.56
    Activations Density 1.346%

    No Known Activations