© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109218
    Prev
    Next
    INDEX
    Explanations

    hoist or scaffold

    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_1_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
    q
    1.53
    .
    1.48
     can
    1.32
     as
    1.29
    л
    1.27
     on
    1.20
    ด
    1.20
     आप
    1.17
    \
    1.13
     is
    1.08
    POSITIVE LOGITS
     principales
    1.02
    unkt
    0.97
    Z
    0.97
     Loretta
    0.95
     specif
    0.95
    ந்தோ
    0.93
    ográf
    0.91
     échanc
    0.91
    X
    0.89
     Ró
    0.89
    Activations Density 0.000%

    No Known Activations