© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 64881
    Prev
    Next
    INDEX
    Explanations

    dialogue turns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    <unused61>
    0.49
     ­
    0.45
    <0xC2>
    0.44
    ­
    0.43
    est
    0.42
    gien
    0.41
    0.41
    <unused62>
    0.41
    ź
    0.40
    orm
    0.39
    POSITIVE LOGITS
    $\--
    0.44
    ὧ
    0.44
     باشه
    0.42
    (^^
    0.42
    olischen
    0.42
    なのか
    0.42
    ාවක්
    0.42
    vartheta
    0.41
    カイ
    0.41
     ಇದು
    0.41
    Activations Density 0.000%

    No Known Activations