© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44475
    Prev
    Next
    INDEX
    Explanations

    arcs and vanes

    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_13_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
     Інтэр
    0.50
    娉
    0.49
    कह
    0.48
     sAlarm
    0.48
     он
    0.47
    AllRef
    0.46
     его
    0.46
    گفت
    0.45
    он
    0.45
    Boost
    0.45
    POSITIVE LOGITS
    cast
    0.63
     '
    0.57
    stream
    0.56
    à
    0.56
    re
    0.55
    ché
    0.54
    chemicals
    0.54
    z
    0.52
     trở
    0.51
    」
    0.49
    Activations Density 0.026%

    No Known Activations