© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83785
    Prev
    Next
    INDEX
    Explanations

    login credentials: username and password

    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_23_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
    orbid
    0.43
    뻥
    0.39
     Living
    0.38
    {
    0.36
     स्थल
    0.36
    _{
    0.36
     '*.
    0.36
     αυτά
    0.36
    ᱑
    0.35
    ata
    0.35
    POSITIVE LOGITS
     driftwood
    0.46
    റി
    0.42
     eucalyptus
    0.40
    全面的
    0.39
    餾
    0.39
    ফতরের
    0.39
     antennae
    0.38
    ضو
    0.38
     intensification
    0.38
    करना
    0.37
    Activations Density 0.003%

    No Known Activations