© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195223
    Prev
    Next
    INDEX
    Explanations

    time is constant

    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_46_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
    possibly
    0.41
    may
    0.40
     potentially
    0.40
    required
    0.38
    potentially
    0.38
     답
    0.37
    minus
    0.36
    eson
    0.36
    殘
    0.36
     confusing
    0.35
    POSITIVE LOGITS
    ว่าเป็น
    0.44
    白的
    0.44
    нів
    0.43
     là
    0.42
     är
    0.41
    IVE
    0.40
     discourses
    0.40
     adalah
    0.39
     DEALINGS
    0.39
     دهید
    0.38
    Activations Density 0.004%

    No Known Activations