© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206904
    Prev
    Next
    INDEX
    Explanations

    worth the wait or risk

    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
    Negative Logits
    り
    0.90
    ме
    0.88
    м
    0.80
    ician
    0.77
    ה
    0.77
    ך
    0.77
    ire
    0.76
    し
    0.76
    н
    0.75
    ని
    0.75
    POSITIVE LOGITS
    t
    1.00
    h
    0.89
    p
    0.88
    <0x89>
    0.80
    ล
    0.77
    the
    0.76
    ต์
    0.75
    리티
    0.75
    G
    0.74
    l
    0.73
    Activations Density 0.000%

    No Known Activations