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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43601
    Prev
    Next
    INDEX
    Explanations

    bow and arrow

    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_3_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
     ensimmä
    0.59
     have
    0.57
     international
    0.57
    ă
    0.56
     industry
    0.54
    u
    0.54
     organis
    0.54
     início
    0.54
    STUD
    0.54
     has
    0.53
    POSITIVE LOGITS
    ל
    0.86
    д
    0.82
    лить
    0.77
    л
    0.74
     Wraith
    0.68
    лиза
    0.66
    га
    0.66
    ле
    0.64
    قي
    0.63
    るので
    0.63
    Activations Density 0.000%

    No Known Activations