© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45024
    Prev
    Next
    INDEX
    Explanations

    #4CAF50

    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_10_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
    m
    0.90
     adhering
    0.76
    <strong>
    0.75
     себе
    0.74
     excruciating
    0.74
     focusing
    0.73
     collaborating
    0.72
     complying
    0.71
     associating
    0.71
     stinging
    0.70
    POSITIVE LOGITS
    OM
    0.93
    ON
    0.91
    C
    0.84
    U
    0.82
    EN
    0.79
    O
    0.79
    Y
    0.79
    OX
    0.77
    X
    0.77
    OH
    0.77
    Activations Density 0.006%

    No Known Activations