© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165353
    Prev
    Next
    INDEX
    Explanations

    medical compression

    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_13_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
    ాలయ
    0.54
    di
    0.53
    kow
    0.52
     Nowak
    0.51
    bfc
    0.49
    vcx
    0.49
    liw
    0.49
    捶
    0.49
    bow
    0.46
    bucks
    0.46
    POSITIVE LOGITS
     el
    0.50
     chronological
    0.49
     dernière
    0.48
     irregular
    0.47
     hydrocarbons
    0.47
     стал
    0.46
    ント
    0.46
     osmosis
    0.45
    ен
    0.45
    タイム
    0.45
    Activations Density 0.000%

    No Known Activations