© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87587
    Prev
    Next
    INDEX
    Explanations

    say "ac" words

    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_60_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
     accord
    1.72
     Accord
    1.72
    Accord
    1.56
     accordion
    1.48
     acord
    1.45
     accords
    1.45
    accord
    1.34
    Accordion
    1.33
    accordion
    1.30
     合
    1.22
    POSITIVE LOGITS
     Ac
    1.76
    Ac
    1.67
    ac
    1.48
     ac
    1.47
     AC
    1.10
    AC
    0.98
     Acme
    0.78
     acorn
    0.78
     acyl
    0.71
     acorns
    0.71
    Activations Density 0.001%

    No Known Activations