© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199948
    Prev
    Next
    INDEX
    Explanations

    reload/charge able

    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_15_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
    з
    0.23
    ρία
    0.21
    л
    0.20
    l
    0.19
     gratifying
    0.19
    z
    0.18
    ж
    0.18
    nis
    0.18
    N
    0.18
    !
    0.18
    POSITIVE LOGITS
     sleepers
    0.19
    ংকের
    0.17
     寸
    0.17
     CONSTRUCTION
    0.17
     konstru
    0.17
     bricks
    0.16
     konstruk
    0.16
     Fenerbah
    0.16
     कढ़ाई
    0.16
     לנו
    0.16
    Activations Density 0.003%

    No Known Activations