© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194257
    Prev
    Next
    INDEX
    Explanations

    language models and functions

    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_9_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
    č
    0.61
     tackling
    0.58
     prodig
    0.57
     in
    0.55
     salicylate
    0.54
    ও
    0.52
     krit
    0.51
     serendip
    0.49
     critically
    0.48
    P
    0.48
    POSITIVE LOGITS
    ڠ
    0.57
    Му
    0.56
    人々
    0.55
    مس
    0.53
    mData
    0.53
    说
    0.53
    説明
    0.52
     Dispon
    0.51
    破損
    0.51
     मसल्स
    0.51
    Activations Density 0.000%

    No Known Activations