© 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. 137671
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
     पल
    0.42
     Becoming
    0.39
    OCUS
    0.38
     रहस्य
    0.38
    ={\
    0.37
     रो
    0.36
     subscribe
    0.36
     কৌশ
    0.36
    ousedown
    0.36
    ဓ
    0.35
    POSITIVE LOGITS
    ✷
    0.38
     Kitt
    0.37
     Shreve
    0.37
    виа
    0.37
    *}$
    0.37
     booth
    0.36
     создать
    0.36
     भंडारण
    0.36
    arai
    0.35
     build
    0.35
    Activations Density 0.003%

    No Known Activations