© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33499
    Prev
    Next
    INDEX
    Explanations

    in many cases

    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
    Negative Logits
    ي
    0.72
    ोत्सव
    0.68
     হইবে
    0.68
     Ла
    0.66
     પ્રતિબિં
    0.66
    ן
    0.62
    ння
    0.61
    ضای
    0.60
    ECs
    0.59
    ει
    0.59
    POSITIVE LOGITS
    '
    0.84
    ’
    0.71
    :
    0.70
    r
    0.67
     that
    0.66
    il
    0.63
     is
    0.62
     the
    0.60
    gning
    0.58
    S
    0.57
    Activations Density 0.001%

    No Known Activations