© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89256
    Prev
    Next
    INDEX
    Explanations

    Nitro generators subscription

    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_11_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
    ما
    0.59
    ي
    0.58
    بي
    0.56
    دي
    0.56
    ئي
    0.51
    ن
    0.50
    </th>
    0.48
    خلي
    0.47
     forme
    0.47
    體
    0.47
    POSITIVE LOGITS
    ausible
    0.60
    (+
    0.54
     नोन
    0.53
    politics
    0.52
    etty
    0.52
     ductility
    0.52
     जोड़ों
    0.51
    imbledon
    0.51
    Duck
    0.51
     관심
    0.50
    Activations Density 0.000%

    No Known Activations