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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249600
    Prev
    Next
    INDEX
    Explanations

    say "itis"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    setActive
    0.42
     separations
    0.39
     표시
    0.37
     Separation
    0.37
     respects
    0.36
    Inflation
    0.35
    焔
    0.35
    靥
    0.35
    infl
    0.34
     infl
    0.34
    POSITIVE LOGITS
    病
    0.57
     disease
    0.55
     doença
    0.54
     بیماری
    0.52
     bệnh
    0.50
     illness
    0.46
     maladie
    0.45
     enfermedad
    0.45
     مرض
    0.45
     Disease
    0.43
    Activations Density 0.002%

    No Known Activations