© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9170
    Prev
    Next
    INDEX
    Explanations

    legends and lore

    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_13_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
    ਈ
    0.65
     conscientious
    0.61
    온
    0.60
     Privilege
    0.54
     wages
    0.53
    ਾਕ
    0.52
    戕
    0.52
     weken
    0.52
    ᓲ
    0.52
     $|
    0.52
    POSITIVE LOGITS
    _
    0.64
    Heroes
    0.64
    </h2>
    0.61
    VA
    0.59
     r
    0.57
    MA
    0.57
    outh
    0.56
     اختر
    0.56
    </u>
    0.54
     t
    0.54
    Activations Density 0.030%

    No Known Activations