© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107621
    Prev
    Next
    INDEX
    Explanations

    Scandinavian and Scotland

    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_2_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
     to
    1.49
    G
    1.38
    9
    1.23
    R
    1.23
    ning
    1.17
     in
    1.13
    К
    1.13
    Z
    1.09
    S
    1.08
    E
    1.08
    POSITIVE LOGITS
    یم
    1.48
    یا
    1.42
     ಡಿ
    1.39
    اوی
    1.38
     régler
    1.38
     aument
    1.36
     Володи
    1.35
    yemek
    1.34
     as
    1.33
    en
    1.30
    Activations Density 0.001%

    No Known Activations