© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8832
    Prev
    Next
    INDEX
    Explanations

    เป็น + noun/adjective

    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_13_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
    ውስ
    0.20
     परिस्थितीत
    0.20
    คะ
    0.20
     unscrupulous
    0.20
     असतो
    0.20
     설명을
    0.19
     orthodontic
    0.19
    슌
    0.19
     anus
    0.19
     simplifié
    0.19
    POSITIVE LOGITS
     is
    0.22
    ﺷ
    0.22
     was
    0.21
    5
    0.21
    ﺑ
    0.20
     sebesar
    0.20
    3
    0.20
     Viator
    0.20
    ﭘ
    0.20
    totally
    0.19
    Activations Density 0.001%

    No Known Activations