© 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. 42351
    Prev
    Next
    INDEX
    Explanations

    more than

    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
     \
    0.76
    };
    0.70
     (
    0.65
    );
    0.63
    서
    0.63
    潦
    0.62
    도
    0.62
    0.61
    ല
    0.61
    μα
    0.60
    POSITIVE LOGITS
    ی
    0.96
    ের
    0.85
    s
    0.78
    วัสดี
    0.78
     کازخستان
    0.75
     Спорттук
    0.74
    sene
    0.71
     that
    0.70
    یب
    0.70
    ों
    0.68
    Activations Density 0.011%

    No Known Activations