© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25273
    Prev
    Next
    INDEX
    Explanations

    Python callable functions

    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_10_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
    t
    0.34
     ща
    0.29
    ະລ
    0.29
     bactéries
    0.29
     syllabus
    0.28
     councillors
    0.28
     cem
    0.27
    ractions
    0.27
     linguistics
    0.27
    RIN
    0.27
    POSITIVE LOGITS
     =
    0.35
    د
    0.31
    可以通过
    0.27
    ור
    0.27
    将
    0.27
    wati
    0.27
    یز
    0.27
    通过
    0.26
    دخل
    0.25
    ية
    0.25
    Activations Density 0.020%

    No Known Activations