© 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. 19539
    Prev
    Next
    INDEX
    Explanations

    pat followed by various words

    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
     sientes
    0.59
     molyb
    0.58
     ث
    0.57
     ratios
    0.57
     regulate
    0.57
    FBSDKError
    0.57
    RationalValue
    0.56
     svom
    0.56
     molde
    0.56
     ボ
    0.55
    POSITIVE LOGITS
    atangan
    0.65
    í
    0.64
    bau
    0.58
    á
    0.58
    is
    0.57
    iny
    0.57
    rai
    0.56
    ini
    0.54
    in
    0.54
     Philippine
    0.54
    Activations Density 0.001%

    No Known Activations