© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260925
    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_10_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
    जग
    1.21
     bit
    1.05
    \
    1.02
    gris
    1.01
    ned
    1.00
    voll
    1.00
     dzi
    0.97
     telle
    0.97
    ன்
    0.97
    inken
    0.97
    POSITIVE LOGITS
    ेशन
    1.26
    <unused23>
    1.21
     inescap
    1.19
    Flagge
    1.19
     ImageData
    1.18
    ௐ
    1.18
    netstandard
    1.16
    мак
    1.14
     kitu
    1.14
    DependentUpon
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.