© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198600
    Prev
    Next
    INDEX
    Explanations

    mirror on the wall

    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_15_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
    杫
    0.55
    㫙
    0.54
    вати
    0.53
    Х
    0.53
    да
    0.52
    rances
    0.52
    мани
    0.50
    闖
    0.49
     অবাধ
    0.49
     СССР
    0.48
    POSITIVE LOGITS
     Är
    0.47
    的空间
    0.45
    აც
    0.44
     Nhi
    0.44
     SIZE
    0.44
     निकालेंगे
    0.44
     Mô
    0.43
     হইলেন
    0.42
    uur
    0.42
    რულ
    0.42
    Activations Density 0.001%

    No Known Activations