© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181100
    Prev
    Next
    INDEX
    Explanations

    transparent borders

    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_24_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ananti
    0.50
    udiantes
    0.47
    ank
    0.46
    aç
    0.46
    apé
    0.45
    ConfigFile
    0.44
     岩
    0.44
     Siamo
    0.43
    borg
    0.43
    ark
    0.42
    POSITIVE LOGITS
     floods
    0.40
    ჯერ
    0.37
    لاین
    0.37
    ವಾಗಿ
    0.37
     flooding
    0.37
     Cec
    0.37
     Ambro
    0.37
    ფი
    0.36
     helpful
    0.36
    ్
    0.36
    Activations Density 0.000%

    No Known Activations