© 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. 232823
    Prev
    Next
    INDEX
    Explanations

    pre-treatment or treatment status

    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
    Not in Any Lists

    No Comments

    Negative Logits
    。
    1.22
    ।
    1.18
    k
    1.15
    as
    1.13
    ק
    1.09
    in
    1.07
    al
    1.07
    ak
    1.07
    n
    1.02
    p
    1.01
    POSITIVE LOGITS
     symbolized
    0.94
     Și
    0.91
     Ș
    0.90
     property
    0.89
     materialized
    0.88
     perché
    0.87
     потому
    0.87
     shimmering
    0.85
     traveled
    0.85
     protože
    0.84
    Activations Density 0.000%

    No Known Activations