© 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. 245626
    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
     instancia
    1.07
     eviden
    0.98
     selezion
    0.96
    㹂
    0.93
    Asimismo
    0.93
     accueille
    0.93
    됩니다
    0.93
     OCPP
    0.91
     सलू
    0.91
     histórica
    0.91
    POSITIVE LOGITS
     Followers
    0.81
     waved
    0.81
     VI
    0.78
    rang
    0.77
     VII
    0.75
    rade
    0.75
    ี
    0.74
     VIII
    0.72
     Dynamic
    0.70
     inspiration
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.