© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12636
    Prev
    Next
    INDEX
    Explanations

    usa, ISO

    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_40_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
    pt
    0.39
     aran
    0.39
     bilateral
    0.38
     Z
    0.37
    зина
    0.36
     consistency
    0.35
     esbo
    0.35
    consistency
    0.35
    orys
    0.35
    畐
    0.35
    POSITIVE LOGITS
    涫
    0.40
    शी
    0.38
     निकालने
    0.38
     Generators
    0.37
    ുകൂ
    0.37
    வியை
    0.37
    ǀ
    0.37
     Themen
    0.36
     mates
    0.36
    าน
    0.35
    Activations Density 0.030%

    No Known Activations