© 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-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197155
    Prev
    Next
    INDEX
    Explanations

    similar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_26_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
     ១
    0.07
     exclusivos
    0.07
    Employer
    0.07
    né
    0.07
     sederhana
    0.07
     घाट
    0.07
    collectibles
    0.07
     sConfig
    0.07
     Econom
    0.07
     [@
    0.07
    POSITIVE LOGITS
    U
    0.07
    ע
    0.07
    人物
    0.07
    ed
    0.07
     खराब
    0.07
    τικού
    0.06
    ადა
    0.06
    P
    0.06
    ×
    0.06
    VERSION
    0.06
    Activations Density 0.011%

    No Known Activations