© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196779
    Prev
    Next
    INDEX
    Explanations

    conditions

    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_15_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
     우리는
    0.63
     gluon
    0.60
     शुरुआ
    0.58
     пур
    0.58
     आम्ही
    0.57
     증가
    0.57
     क
    0.57
     अपघात
    0.57
     irradiated
    0.57
     suport
    0.56
    POSITIVE LOGITS
     (
    0.55
    的过程中
    0.54
    asi
    0.53
    نتي
    0.50
    的市场
    0.49
    顿
    0.47
    dal
    0.46
    ,
    0.45
    !
    0.45
    re
    0.45
    Activations Density 0.000%

    No Known Activations