© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17983
    Prev
    Next
    INDEX
    Explanations

    basketball, NBA, WNBA, scoring, play, defensive

    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_40_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
    atora
    0.41
    駆動
    0.40
    内の
    0.40
    phol
    0.39
    रखाव
    0.39
    istel
    0.37
    </table>
    0.37
    zieh
    0.37
    DoS
    0.37
     buoyancy
    0.35
    POSITIVE LOGITS
     кро
    0.44
     rela
    0.40
    ostí
    0.40
     Title
    0.38
     titoli
    0.37
    穿
    0.37
    $^{
    0.36
     kro
    0.36
    Lore
    0.35
     Стро
    0.35
    Activations Density 0.014%

    No Known Activations