© 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. 121427
    Prev
    Next
    INDEX
    Explanations

    top/bottom

    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
    Negative Logits
    i
    1.05
    am
    0.91
    is
    0.82
    ي
    0.82
    el
    0.79
    ol
    0.73
    ে
    0.70
                                 
    0.70
    ingredients
    0.69
    ଼
    0.68
    POSITIVE LOGITS
     on
    0.74
    ך
    0.65
    ž
    0.62
     njih
    0.60
    из
    0.60
    ച്ച
    0.59
     twor
    0.59
    يل
    0.58
     znajdują
    0.58
     podkre
    0.58
    Activations Density 0.001%

    No Known Activations