© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140102
    Prev
    Next
    INDEX
    Explanations

    password verification

    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_37_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
     spice
    0.42
     Bin
    0.39
     Louisa
    0.37
     BM
    0.37
     आएगा
    0.36
     pasture
    0.36
     BCA
    0.36
    ;%%
    0.35
     Negotiations
    0.35
    ్వర
    0.35
    POSITIVE LOGITS
    চ্ছিন্ন
    0.39
    ব্রত
    0.38
    ())->
    0.37
    Dip
    0.37
    sterile
    0.37
    ALT
    0.36
    AuthController
    0.36
     doigts
    0.36
    Phen
    0.36
     sterilized
    0.35
    Activations Density 0.000%

    No Known Activations