© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148567
    Prev
    Next
    INDEX
    Explanations

    speed, velocity, or coordinate assignment

    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_23_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
    љи
    0.41
    ାଇ
    0.41
     treasures
    0.40
     जहर
    0.40
    lockSeconds
    0.39
     hydrogens
    0.39
    및
    0.39
    ķ
    0.39
     দেখেছি
    0.38
    ್ಣ
    0.38
    POSITIVE LOGITS
     axit
    0.40
     Coh
    0.37
     inter
    0.36
    crud
    0.36
     Cart
    0.36
     cohort
    0.35
     Grit
    0.35
     интер
    0.35
     Debate
    0.34
     cá
    0.34
    Activations Density 0.003%

    No Known Activations