© 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. 76039
    Prev
    Next
    INDEX
    Explanations

    movement from

    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
     Stop
    0.37
     Students
    0.35
    ⁱ
    0.35
     ([
    0.35
    멈
    0.35
    截止
    0.35
    三十
    0.35
     House
    0.34
     утвер
    0.34
     Cottage
    0.34
    POSITIVE LOGITS
    ":"",
    0.40
    стрии
    0.39
    /).
    0.38
    oreille
    0.38
     légumes
    0.38
     cơm
    0.37
    ouwen
    0.37
     cereal
    0.37
    ulah
    0.36
    ()==
    0.36
    Activations Density 0.002%

    No Known Activations