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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137096
    Prev
    Next
    INDEX
    Explanations

    payment requests

    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
     oddly
    0.57
    嬗
    0.56
    𝙷
    0.53
     Constituição
    0.52
     Когда
    0.50
     кораб
    0.49
     iPads
    0.49
     Sarm
    0.49
     Ấ
    0.49
    рье
    0.48
    POSITIVE LOGITS
     제가
    0.50
    な
    0.50
     cost
    0.50
     diagnosis
    0.50
     kết
    0.46
     ado
    0.46
     connection
    0.46
    four
    0.46
    skull
    0.46
    diagnosis
    0.46
    Activations Density 0.003%

    No Known Activations