© 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. 139945
    Prev
    Next
    INDEX
    Explanations

    saving files or items

    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
    鑼
    0.39
    ೋ
    0.38
    malt
    0.37
     allied
    0.36
    Atoi
    0.36
     impermeable
    0.36
     phenomen
    0.36
     malt
    0.36
    Prior
    0.35
    ⎞
    0.35
    POSITIVE LOGITS
     Saving
    0.45
     Saved
    0.43
     pele
    0.43
     Savings
    0.41
     Automated
    0.41
    aughton
    0.41
     Saves
    0.40
    udrait
    0.40
     saving
    0.40
     Chief
    0.39
    Activations Density 0.004%

    No Known Activations