© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107704
    Prev
    Next
    INDEX
    Explanations

    cultivation, occultation

    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_1_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
    t
    1.20
    the
    1.15
    ровать
    1.09
    ।--
    0.99
     выражение
    0.98
    ма
    0.96
     perfused
    0.95
    tól
    0.93
     المثلثيه
    0.93
    っていない
    0.92
    POSITIVE LOGITS
     I
    1.35
    ↵↵
    1.21
    em
    1.21
    </h2>
    1.16
    ING
    1.10
    I
    1.09
    你
    1.07
    大
    1.04
    个
    1.02
    ell
    1.02
    Activations Density 0.001%

    No Known Activations