© 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. 74680
    Prev
    Next
    INDEX
    Explanations

    Let them

    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
     кеңселер
    0.40
     سوچ
    0.39
     comforting
    0.37
     چاہتے
    0.37
     постара
    0.37
     চাই
    0.36
     contemplate
    0.36
     Seventy
    0.36
    Fifty
    0.36
    议
    0.35
    POSITIVE LOGITS
    맵
    0.42
    product
    0.39
    xf
    0.38
    レ
    0.38
     cq
    0.38
    ప్రదేశ్
    0.38
    json
    0.38
     vocês
    0.38
    Product
    0.38
     महंगे
    0.38
    Activations Density 0.002%

    No Known Activations