© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219231
    Prev
    Next
    INDEX
    Explanations

    reviews and nominations

    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_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
     Верх
    0.38
     Typography
    0.38
     Existem
    0.37
     empfehlen
    0.36
    ച
    0.36
     Câu
    0.36
     OPS
    0.36
    icketts
    0.36
    enze
    0.35
     subordination
    0.34
    POSITIVE LOGITS
    带来的
    0.43
    Coast
    0.40
    polar
    0.40
     awaiting
    0.39
    ោះ
    0.39
    خواهد
    0.38
    ೕ
    0.38
     ناقص
    0.38
    带来
    0.37
     ill
    0.37
    Activations Density 0.000%

    No Known Activations