© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4867
    Prev
    Next
    INDEX
    Explanations

    sirve caliente, opcional, recipe

    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_39_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
     بررسی
    0.46
    寿司
    0.44
    不動
    0.41
    歐
    0.40
     cooks
    0.40
     तुमसे
    0.39
     আইনশৃঙ্খলা
    0.39
    ettu
    0.38
    کر
    0.38
    欧
    0.38
    POSITIVE LOGITS
     wą
    0.45
     aconsel
    0.43
     exquis
    0.42
     Gur
    0.40
     pior
    0.39
    Gur
    0.39
     каче
    0.38
    │
    0.38
     delikat
    0.37
     sprem
    0.36
    Activations Density 0.118%

    No Known Activations