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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15040
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_19_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ((
    1.43
    (((
    1.06
     ((
    1.05
    [(
    1.00
    ('\
    0.98
    if
    0.95
    (('
    0.93
    ((\
    0.92
    for
    0.88
    (&(
    0.88
    POSITIVE LOGITS
     public
    0.78
     Vergleich
    0.77
     impl
    0.73
     graduate
    0.72
     Committee
    0.71
     private
    0.68
     sympathy
    0.67
     Private
    0.67
     noble
    0.66
     אַ
    0.66
    Activations Density 0.066%

    No Known Activations