© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139200
    Prev
    Next
    INDEX
    Explanations

    social studies

    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_12_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
     !
    0.64
    mostly
    0.54
    $
    0.53
     cuisine
    0.52
    út
    0.52
    ють
    0.52
    O
    0.51
    bit
    0.50
    Oil
    0.49
    GG
    0.49
    POSITIVE LOGITS
    㛲
    0.55
    冎
    0.55
     Andal
    0.50
    原子炉
    0.48
     banderas
    0.48
    昉
    0.47
    حيان
    0.47
    伯
    0.47
     ponder
    0.47
     enterr
    0.46
    Activations Density 0.000%

    No Known Activations