© 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. 135521
    Prev
    Next
    INDEX
    Explanations

    lodged in

    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
    W
    1.36
    C
    1.32
    X
    1.27
    F
    1.27
    H
    1.26
    B
    1.24
    Z
    1.23
    н
    1.15
    O
    1.07
    க
    1.05
    POSITIVE LOGITS
    ной
    1.09
    il
    1.02
     a
    0.99
    t
    0.94
     cooperate
    0.84
     '
    0.83
     scala
    0.82
     configuração
    0.82
     fragile
    0.82
     at
    0.81
    Activations Density 0.000%

    No Known Activations