© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134377
    Prev
    Next
    INDEX
    Explanations

    wash, vert, and revert

    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_6_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
    s
    1.13
    at
    1.02
    IN
    0.91
    IA
    0.86
     at
    0.84
    ET
    0.83
    B
    0.83
    new
    0.82
    re
    0.82
     for
    0.82
    POSITIVE LOGITS
    ও
    0.84
    も
    0.84
    蹌
    0.84
    ϓ
    0.79
    ↵
    0.78
    もら
    0.77
    ใน
    0.77
     شدہ
    0.76
    在
    0.75
    る
    0.75
    Activations Density 0.000%

    No Known Activations