© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 152025
    Prev
    Next
    INDEX
    Explanations

    names

    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_59_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
     HE
    0.52
     Vin
    0.49
    Ха
    0.43
    Vin
    0.43
    하
    0.42
     Ха
    0.41
     ها
    0.41
    ហា
    0.40
     하
    0.40
     Inquisition
    0.39
    POSITIVE LOGITS
    Johann
    0.73
     Heinrich
    0.69
     Johann
    0.68
    Johannes
    0.65
    Heinrich
    0.65
     Johannes
    0.64
    Johnny
    0.61
     Hendrik
    0.57
     हेनरी
    0.56
     Johnny
    0.55
    Activations Density 0.004%

    No Known Activations