© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121805
    Prev
    Next
    INDEX
    Explanations

    slide 1: title

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    いろいろ
    0.84
    ?]
    0.74
    ע
    0.72
    其他
    0.71
     ожида
    0.70
    うまく
    0.70
    ）；
    0.69
     ?)
    0.69
    !);
    0.68
     utilisateur
    0.68
    POSITIVE LOGITS
    la
    0.91
    de
    0.79
     (
    0.79
    ll
    0.71
    l
    0.71
    ne
    0.69
    kv
    0.66
    ria
    0.66
    d
    0.66
    da
    0.65
    Activations Density 0.002%

    No Known Activations