© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193397
    Prev
    Next
    INDEX
    Explanations

    slug generation for titles

    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_27_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
     últ
    0.40
     अधिकतम
    0.39
     diseñado
    0.37
     máxim
    0.37
     excepc
    0.36
    issances
    0.36
    结局
    0.36
    下的
    0.35
     irresist
    0.35
    \";
    0.35
    POSITIVE LOGITS
     pesticides
    0.45
     refrigerators
    0.43
    藺
    0.42
     Hebrew
    0.42
     Ted
    0.41
     یخچال
    0.41
     pastries
    0.40
     lettuce
    0.39
    acotta
    0.38
     cosmetics
    0.38
    Activations Density 0.001%

    No Known Activations