© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59394
    Prev
    Next
    INDEX
    Explanations

    TODO comments

    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_11_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
    кс
    0.57
     violates
    0.56
    禧
    0.54
    𝕥
    0.54
    霭
    0.54
    шает
    0.53
     från
    0.53
     мм
    0.52
    temperatur
    0.52
     więc
    0.52
    POSITIVE LOGITS
     Undo
    0.55
     وحده
    0.54
    elah
    0.53
     Municipality
    0.52
    atical
    0.52
    लावा
    0.51
    สังคม
    0.51
    al
    0.50
    ing
    0.50
    ロ
    0.50
    Activations Density 0.000%

    No Known Activations