Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11042
    Prev
    Next
    INDEX
    Explanations

    indents at the beginning of lines

    oai_token-act-pair · gemini-2.0-flash

    whitespace and special characters

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

    <eos>

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.16
     itſelf
    -1.10
     myſelf
    -1.09
    ⓧ
    -1.08
     مرئيه
    -1.05
     propOrder
    -1.05
    principalColumn
    -1.03
     незавершена
    -1.03
    mybatisplus
    -1.02
     CreateTagHelper
    -1.02
    POSITIVE LOGITS
     
    1.16
    <eos>
    0.69
     P
    0.68
     *
    0.68
     F
    0.67
     */
    0.67
     >
    0.66
     (
    0.66
     -
    0.64
     C
    0.63
    Activations Density 1.234%

    No Known Activations