© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192352
    Prev
    Next
    INDEX
    Explanations

    Horizon Worlds, Line, Electric

    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_4_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
    es
    0.35
    team
    0.34
    am
    0.32
    waffe
    0.32
    to
    0.29
    m
    0.29
    tr
    0.29
    larda
    0.29
    teams
    0.28
    tor
    0.28
    POSITIVE LOGITS
    是
    0.33
    ó
    0.28
    I
    0.27
    ۔
    0.27
    á
    0.27
    ä
    0.26
     planeta
    0.25
    א
    0.25
     höher
    0.24
     embed
    0.23
    Activations Density 0.005%

    No Known Activations