© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124211
    Prev
    Next
    INDEX
    Explanations

    grating or shredding

    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_37_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
    相互
    0.45
    汁
    0.44
    銑
    0.43
     sogg
    0.42
     entrant
    0.41
     vinaig
    0.41
     Sling
    0.41
    bigskip
    0.40
    抽出
    0.40
    ності
    0.39
    POSITIVE LOGITS
    ậm
    0.38
    Ave
    0.37
    ync
    0.35
     জায়গায়
    0.35
    AsFactors
    0.35
    cons
    0.34
    loads
    0.34
    ፀ
    0.34
    AVE
    0.34
    keyframes
    0.34
    Activations Density 0.002%

    No Known Activations