© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69386
    Prev
    Next
    INDEX
    Explanations

    pick and choose

    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_46_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
     elusive
    0.71
     el
    0.67
     j
    0.63
     evaded
    0.50
     els
    0.45
     evas
    0.45
     leaving
    0.44
     evade
    0.43
    Burning
    0.42
     Leave
    0.42
    POSITIVE LOGITS
    槌
    0.39
     concordance
    0.37
     firing
    0.37
    oustache
    0.37
     অভ
    0.37
    OUGH
    0.37
     ವ್ಯಾ
    0.36
    _{{\
    0.36
    ጾ
    0.36
     Dak
    0.36
    Activations Density 0.023%

    No Known Activations