© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58758
    Prev
    Next
    INDEX
    Explanations

    author, genre, trilogy

    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_11_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
     hydrocarbon
    0.50
    ﻦ
    0.49
     biotic
    0.48
    酪
    0.48
     elucidate
    0.47
    ル
    0.47
    ५
    0.47
     ಏಕೆಂದರೆ
    0.47
    र्क
    0.46
     rész
    0.46
    POSITIVE LOGITS
     spf
    0.60
     সমাধি
    0.57
    霭
    0.55
     SPF
    0.52
     Squirrel
    0.51
     السما
    0.50
     எழு
    0.50
    အချိန်
    0.50
    Supervisor
    0.49
     embl
    0.49
    Activations Density 0.031%

    No Known Activations