© 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. 47041
    Prev
    Next
    INDEX
    Explanations

    progress percentage updates

    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
    ation
    0.66
    /
    0.54
     ích
    0.51
    hibit
    0.49
    ுள்ளனர்
    0.49
    orems
    0.49
    man
    0.48
     चाहता
    0.47
     تحفظ
    0.47
    ありました
    0.46
    POSITIVE LOGITS
     Progressive
    0.91
    ي
    0.90
    ם
    0.81
     Progressives
    0.75
     progres
    0.74
    ი
    0.74
     PROGRESS
    0.73
    ों
    0.71
    Т
    0.71
     progressive
    0.70
    Activations Density 0.004%

    No Known Activations