© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125198
    Prev
    Next
    INDEX
    Explanations

    falls far outside

    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_37_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
     ikke
    0.54
     nicht
    0.53
    不是很
    0.49
     não
    0.48
    不太
    0.48
     не
    0.45
    ไม่
    0.45
    Ξ
    0.44
    não
    0.44
    nicht
    0.43
    POSITIVE LOGITS
     전혀
    1.09
    全く
    1.01
     совершенно
    0.93
     completely
    0.92
    全然
    0.89
     Completely
    0.89
     utterly
    0.87
     абсолютно
    0.86
     बिलकुल
    0.86
     völlig
    0.86
    Activations Density 0.318%

    No Known Activations