© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171031
    Prev
    Next
    INDEX
    Explanations

    punctuation symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     SETUP
    0.42
     forma
    0.37
    itaires
    0.36
     nasz
    0.35
     incremental
    0.33
     ones
    0.33
     V
    0.33
    ौरा
    0.32
     systematic
    0.31
    खम
    0.31
    POSITIVE LOGITS
    )،
    0.44
    >),
    0.44
     ወይም
    0.43
    ”،
    0.42
    ፣
    0.42
     অথবা
    0.41
    >?
    0.41
    ;#
    0.41
    '।
    0.41
    ↵↵↵↵↵↵↵↵↵↵
    0.41
    Activations Density 0.000%

    No Known Activations