© 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. 200544
    Prev
    Next
    INDEX
    Explanations

    ... and then

    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
     a
    1.23
    -
    1.02
     on
    0.98
     at
    0.92
    0
    0.90
     famed
    0.86
     grassy
    0.86
     –
    0.85
     not
    0.80
     ~
    0.77
    POSITIVE LOGITS
    Щ
    0.92
    ным
    0.91
    。
    0.90
    ４
    0.87
    f
    0.86
    ３
    0.86
    िरण
    0.84
    G
    0.84
    )。
    0.83
    T
    0.82
    Activations Density 0.003%

    No Known Activations