© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136370
    Prev
    Next
    INDEX
    Explanations

    API tokens and services

    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_12_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
     *)
    0.63
     Spotify
    0.54
    ير
    0.51
     Sonos
    0.50
     initiate
    0.49
    முடைய
    0.49
    spotify
    0.48
    啟
    0.48
     AP
    0.47
    स्को
    0.46
    POSITIVE LOGITS
     downsizing
    0.61
    gement
    0.59
    gning
    0.58
    ল্যান্ডের
    0.54
     mishaps
    0.53
     possano
    0.50
    জন
    0.50
    bleau
    0.50
    لے
    0.49
     ಪ್ರಮಾಣ
    0.49
    Activations Density 0.007%

    No Known Activations