© 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. 48985
    Prev
    Next
    INDEX
    Explanations

    what works

    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
     sizable
    0.31
    |}
    0.29
     כמה
    0.29
     ముఖ్య
    0.29
    ভিয়েতনাম
    0.28
    dst
    0.28
    туре
    0.27
     Cez
    0.27
    ֔
    0.27
    ouss
    0.27
    POSITIVE LOGITS
    School
    0.35
     lou
    0.32
     professors
    0.32
     heads
    0.31
     drives
    0.31
     uni
    0.31
    zeki
    0.31
     ع
    0.31
     stood
    0.30
     arguing
    0.29
    Activations Density 0.021%

    No Known Activations