© 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
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92226
    Prev
    Next
    INDEX
    Explanations

    provided "as is"

    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
     කැ
    0.58
     бекер
    0.57
     بسي
    0.57
     cárc
    0.56
     honti
    0.56
     októ
    0.56
    ៧
    0.54
     مي‌
    0.53
     ရှိ
    0.53
     كنت
    0.52
    POSITIVE LOGITS
    (
    0.55
    I
    0.55
    Indigenous
    0.54
    If
    0.52
    ือ
    0.52
    0
    0.52
     and
    0.51
     East
    0.50
    By
    0.50
     Type
    0.50
    Activations Density 0.001%

    No Known Activations