© 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. 135526
    Prev
    Next
    INDEX
    Explanations

    turn

    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
    지
    1.10
    as
    1.07
    కు
    1.05
    м
    1.04
     dover
    0.90
    л
    0.90
    ный
    0.88
     doux
    0.88
     пакет
    0.87
     orgánica
    0.86
    POSITIVE LOGITS
    ),
    1.16
    {
    1.10
    ست
    1.09
    <
    1.09
    ured
    1.02
    int
    0.99
    $,
    0.98
    )
    0.96
    )。
    0.93
    confirmed
    0.93
    Activations Density 0.001%

    No Known Activations