© 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. 41800
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
     درخواست
    0.46
     jetzt
    0.42
     বয়স্ক
    0.41
     Database
    0.41
    ẻ
    0.41
     Bibliothek
    0.40
     aggior
    0.40
     Jetzt
    0.40
     minul
    0.39
    স্কার
    0.39
    POSITIVE LOGITS
    мель
    0.40
     밀
    0.39
     mils
    0.39
    rité
    0.38
    යින්
    0.38
     drags
    0.37
     mil
    0.37
    London
    0.36
     hardcore
    0.36
     coupé
    0.36
    Activations Density 0.000%

    No Known Activations