© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109255
    Prev
    Next
    INDEX
    Explanations

    negotiations

    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_1_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
     for
    1.45
    ר
    1.33
    as
    1.29
    at
    1.22
    |}
    1.16
    x
    1.16
    ar
    1.13
     shouldn
    1.13
    ach
    1.11
    ر
    1.09
    POSITIVE LOGITS
    с
    1.45
    Figura
    1.39
    ﮏ
    1.39
    ON
    1.38
    ച്ച്
    1.37
        
    1.34
     березня
    1.34
     botão
    1.32
    ları
    1.31
    める
    1.30
    Activations Density 0.000%

    No Known Activations