© 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. 232970
    Prev
    Next
    INDEX
    Explanations

    jenner, hilton

    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
    た
    1.06
    ON
    0.96
    یان
    0.89
    は
    0.88
    י
    0.83
    А
    0.83
    נ
    0.81
    ます
    0.80
    AK
    0.80
     município
    0.78
    POSITIVE LOGITS
    st
    1.31
    ’
    1.26
    ik
    1.19
    w
    1.19
    als
    1.16
    v
    1.14
    z
    1.09
    c
    1.05
    s
    1.05
    \
    1.02
    Activations Density 0.000%

    No Known Activations