© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75965
    Prev
    Next
    INDEX
    Explanations

    On

    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_31_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
     hva
    0.40
    壅
    0.39
    ALWAYS
    0.38
     ಕೇಳ
    0.38
    რება
    0.38
    に関して
    0.37
    對
    0.37
    អា
    0.37
    都能
    0.36
    對於
    0.36
    POSITIVE LOGITS
    紝
    0.40
     Gente
    0.37
     PrintWriter
    0.36
     границы
    0.35
     electrodes
    0.35
     BufferedReader
    0.35
     кнопки
    0.34
     মেঝে
    0.34
     McKay
    0.34
     চোখের
    0.34
    Activations Density 0.000%

    No Known Activations