© 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-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245594
    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_11_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
    LPTMR
    1.08
    ਿੱ
    1.08
    '];
    1.06
    ედერ
    1.04
    checker
    1.03
     fabs
    1.01
     कमी
    1.01
     momencie
    1.01
    ான
    0.99
     $*$-
    0.98
    POSITIVE LOGITS
     bağlı
    1.22
     ребята
    1.14
     Фор
    1.06
    unning
    1.05
     pave
    1.01
     cht
    1.00
     Umgebung
    1.00
     Walnut
    1.00
    amalla
    1.00
    ellige
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.