© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90431
    Prev
    Next
    INDEX
    Explanations

    competition title elements

    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_3_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
     in
    0.79
     \
    0.77
     de
    0.74
    o
    0.73
     won
    0.72
    OR
    0.71
     会
    0.70
    uleiro
    0.68
    EN
    0.68
     miserable
    0.68
    POSITIVE LOGITS
    но
    0.79
    자
    0.74
     individus
    0.73
    ອາຫານ
    0.73
     мастеров
    0.71
    <0x80>
    0.69
    ときは
    0.68
     городах
    0.66
    タリー
    0.66
    явля
    0.65
    Activations Density 0.017%

    No Known Activations