© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247223
    Prev
    Next
    INDEX
    Explanations

    url prefix ://

    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_40_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
    澎
    0.40
    gat
    0.39
    இந்திய
    0.39
    theria
    0.39
    ogly
    0.38
    Sandbox
    0.37
     பற
    0.36
    แล
    0.36
    অর্
    0.35
    כי
    0.35
    POSITIVE LOGITS
     Escape
    0.42
     Johnson
    0.42
     UINavigation
    0.42
     Euro
    0.41
    卒
    0.40
     Yukawa
    0.39
     Plus
    0.38
    essional
    0.37
     DISE
    0.37
     cdr
    0.37
    Activations Density 0.000%

    No Known Activations