© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229346
    Prev
    Next
    INDEX
    Explanations

    sensory information processing

    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_6_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
    h
    1.23
    -
    1.22
     Usted
    1.16
     you
    1.09
     escrib
    1.06
    -"+
    1.05
    z
    1.04
    -+
    1.03
    v
    1.02
    w
    1.02
    POSITIVE LOGITS
    은
    1.09
    이면
    0.93
    는
    0.92
     femoral
    0.88
    จะ
    0.88
    kim
    0.86
    یده
    0.86
    ‌ی
    0.86
     cannula
    0.85
    ಕ್ಕೆ
    0.84
    Activations Density 0.001%

    No Known Activations