© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215991
    Prev
    Next
    INDEX
    Explanations

    off

    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_5_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
    </h3>
    0.98
    ী
    0.95
    <0x0D>
    0.95
    。
    0.84
    ้า
    0.82
    ant
    0.81
    い
    0.80
    </h4>
    0.79
    ется
    0.79
    ，
    0.77
    POSITIVE LOGITS
    ne
    1.30
    на
    1.08
    on
    0.97
     on
    0.88
    ८
    0.87
    Р
    0.79
    आई
    0.77
    స
    0.76
    나
    0.75
    x
    0.75
    Activations Density 0.000%

    No Known Activations