© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257649
    Prev
    Next
    INDEX
    Explanations

    completion or handover

    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_22_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
    abras
    0.45
    }}}{
    0.41
     abrasion
    0.41
     accretion
    0.40
    ালক
    0.40
     abrasive
    0.40
     مخطط
    0.40
     fibrillation
    0.39
     २०२
    0.39
     unsh
    0.38
    POSITIVE LOGITS
    éns
    0.46
     Freight
    0.43
    Properties
    0.42
     সাঁ
    0.41
     Improve
    0.41
     Thủ
    0.41
    窑
    0.41
     sẵn
    0.40
     hvert
    0.40
     born
    0.40
    Activations Density 0.009%

    No Known Activations