© 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. 139875
    Prev
    Next
    INDEX
    Explanations

    Mach speeds

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Neutral
    0.43
     neutrality
    0.43
     Provisions
    0.43
     Neutral
    0.41
    neutral
    0.39
    Discord
    0.39
    ソ
    0.38
     Soto
    0.38
     neutralization
    0.38
     ආහාර
    0.37
    POSITIVE LOGITS
    τρέ
    0.40
    gesch
    0.39
     Bartosz
    0.39
     lspace
    0.39
     episcopal
    0.38
     Bishop
    0.38
     unconsciously
    0.38
    Ǥ
    0.38
    ಳಿ
    0.37
     Lyn
    0.37
    Activations Density 0.004%

    No Known Activations