© 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. 168058
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    ██
    0.32
    чком
    0.32
     علیحد
    0.30
    checking
    0.30
    Checking
    0.29
    Interview
    0.29
    Educational
    0.29
    Importance
    0.28
     ComVisible
    0.28
    reements
    0.28
    POSITIVE LOGITS
     Lauf
    0.33
     Lacy
    0.32
     initial
    0.31
     మద్యం
    0.31
     implicit
    0.31
     ř
    0.31
     logical
    0.30
     Babylon
    0.30
     raw
    0.30
     suction
    0.30
    Activations Density 0.008%

    No Known Activations