© 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. 165176
    Prev
    Next
    INDEX
    Explanations

    her orally or sister

    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
    证券
    0.36
    ⱱ
    0.36
    Ƭ
    0.35
    iscilla
    0.34
     vertebrae
    0.34
    顎
    0.34
    isphere
    0.34
     విజయ
    0.34
     ઉત્પાદ
    0.34
     wiadomo
    0.34
    POSITIVE LOGITS
    컨
    0.37
    创始人
    0.36
    रल
    0.36
     sustains
    0.36
     bohater
    0.36
    ാരം
    0.36
     দেখেন
    0.35
     convirtió
    0.35
     испыты
    0.34
    攢
    0.34
    Activations Density 0.007%

    No Known Activations