© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30002
    Prev
    Next
    INDEX
    Explanations

    B

    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_7_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
     =
    0.33
    n
    0.32
    ↵
    0.31
                 
    0.30
     ETFs
    0.30
     OEM
    0.29
    u
    0.28
     AB
    0.28
     från
    0.27
     eenvoudig
    0.27
    POSITIVE LOGITS
    с
    0.38
    。
    0.31
    но
    0.30
    س
    0.29
    、
    0.28
    ба
    0.27
    ح
    0.27
    ス
    0.27
    او
    0.26
    в
    0.26
    Activations Density 0.037%

    No Known Activations