© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200180
    Prev
    Next
    INDEX
    Explanations

    white wine or sausage

    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_12_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
    פת
    0.55
     Hokkaido
    0.54
    NGTH
    0.54
     পোষ্ট
    0.52
    涀
    0.52
     Blom
    0.52
     Gastroenter
    0.51
    恈
    0.51
     Santorini
    0.50
    直径
    0.50
    POSITIVE LOGITS
    er
    0.63
     краски
    0.52
    존
    0.51
     arduous
    0.50
    svet
    0.50
    lé
    0.50
    ŭ
    0.49
     tedious
    0.47
     tiresome
    0.46
     usual
    0.46
    Activations Density 0.000%

    No Known Activations