© 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. 90174
    Prev
    Next
    INDEX
    Explanations

    director names and verbs of directing

    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
    ព័
    0.32
    balanced
    0.30
     Hun
    0.28
    ontal
    0.26
     roman
    0.26
    resc
    0.26
     expedi
    0.26
    膠
    0.26
    革
    0.26
     responsive
    0.25
    POSITIVE LOGITS
     Austria
    0.29
     giriş
    0.28
     provoz
    0.27
    وبر
    0.26
    Austria
    0.26
     Österreich
    0.26
     controlled
    0.26
     nieuw
    0.26
     öffent
    0.26
    ල්ල
    0.25
    Activations Density 0.002%

    No Known Activations