© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 209936
    Prev
    Next
    INDEX
    Explanations

    educational content

    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_43_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
     give
    1.88
     Give
    1.80
    Give
    1.77
     giving
    1.73
    give
    1.66
    給
    1.66
     gives
    1.63
     gave
    1.61
     Gives
    1.60
     Giving
    1.56
    POSITIVE LOGITS
    )$;
    0.37
    |=|
    0.37
    guid
    0.36
     جیک
    0.36
    yf
    0.36
    stap
    0.34
     Thing
    0.34
    clean
    0.33
     જી
    0.33
    CTA
    0.33
    Activations Density 0.031%

    No Known Activations