© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206338
    Prev
    Next
    INDEX
    Explanations

    ://

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    udence
    0.43
    সাই
    0.40
    ctus
    0.40
     Ribbon
    0.37
    يمي
    0.35
     Debate
    0.35
     debate
    0.34
    綬
    0.34
     Membership
    0.34
     Liv
    0.33
    POSITIVE LOGITS
     chu
    0.46
     tinh
    0.42
     Чу
    0.41
    ంతరం
    0.40
     അത്
    0.39
     INDEX
    0.38
    चित
    0.38
    િત
    0.37
    فك
    0.37
     malloc
    0.37
    Activations Density 0.000%

    No Known Activations