© 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. 38713
    Prev
    Next
    INDEX
    Explanations

    TinEye, TinyPNG

    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
    2
    0.82
    рт
    0.80
    ﺭ
    0.77
    తో
    0.70
    1
    0.70
    seas
    0.69
    க்க
    0.68
    iere
    0.68
    was
    0.66
    на
    0.66
    POSITIVE LOGITS
    م
    1.01
     práticas
    0.66
    ad
    0.63
     behalf
    0.62
    ar
    0.61
    );
    0.56
     ago
    0.56
     ע
    0.56
    an
    0.55
    ور
    0.55
    Activations Density 0.002%

    No Known Activations