© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136563
    Prev
    Next
    INDEX
    Explanations

    makes a difference

    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_12_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
    ).
    0.71
    );
    0.65
     bisque
    0.62
    ).\\
    0.61
     осмо
    0.57
     о
    0.56
    …)
    0.56
     cursing
    0.56
     уди
    0.55
     canceling
    0.54
    POSITIVE LOGITS
    al
    0.76
    ה
    0.66
    لون
    0.61
    ле
    0.60
    as
    0.60
     게임
    0.58
    ença
    0.57
    game
    0.57
    (
    0.55
    Game
    0.54
    Activations Density 0.000%

    No Known Activations