© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36706
    Prev
    Next
    INDEX
    Explanations

    organizations and their functions

    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_50_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
    "...
    0.48
    "[
    0.38
    子里
    0.36
    чої
    0.35
     συνα
    0.35
    "\
    0.35
    '...
    0.35
    \"\
    0.34
    ".
    0.34
    $\
    0.34
    POSITIVE LOGITS
    􏰁
    0.39
    див
    0.37
     Ongoing
    0.36
     approxim
    0.35
    ɥ
    0.35
    вор
    0.35
    sched
    0.34
     उमेश
    0.34
     Оба
    0.33
     Jed
    0.33
    Activations Density 0.003%

    No Known Activations