© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88675
    Prev
    Next
    INDEX
    Explanations

    capisce, ious, ci, isce

    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_3_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
     capturing
    0.82
     Capture
    0.77
     capture
    0.71
    리
    0.71
     capitán
    0.68
    ết
    0.66
     कप्तान
    0.65
     cáps
    0.65
     Captured
    0.64
    ít
    0.64
    POSITIVE LOGITS
    ו
    0.95
    ,
    0.94
    I
    0.79
    ש
    0.65
    و
    0.64
    il
    0.63
    W
    0.62
    Utah
    0.59
    ون
    0.59
     desenvolv
    0.59
    Activations Density 0.005%

    No Known Activations