© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49482
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    多かった
    0.40
    轧
    0.38
    razine
    0.38
     Yal
    0.37
     Pasand
    0.37
     файла
    0.37
     Mg
    0.37
     तात्
    0.37
     Perak
    0.36
     existir
    0.36
    POSITIVE LOGITS
    கரு
    0.40
    ිර
    0.39
    PRI
    0.39
    vég
    0.38
    PROC
    0.38
     zona
    0.38
    驱
    0.38
    при
    0.37
     dilemma
    0.37
    気に
    0.37
    Activations Density 0.000%

    No Known Activations