© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74741
    Prev
    Next
    INDEX
    Explanations

    .

    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
    Negative Logits
     굉장
    0.37
     சுவாச
    0.37
     contributes
    0.36
     noun
    0.35
     სწ
    0.35
    孫
    0.35
     manpower
    0.35
     naturali
    0.35
    녕하십니까
    0.34
     bean
    0.34
    POSITIVE LOGITS
    ിക്കുകയും
    0.40
     Issued
    0.38
    ลง
    0.38
    ærk
    0.36
    hasil
    0.36
    Doing
    0.36
     ইহাদের
    0.36
    %@",
    0.36
     दिल
    0.36
    ecer
    0.36
    Activations Density 0.003%

    No Known Activations