© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13661
    Prev
    Next
    INDEX
    Explanations

    watch begins, watch vigil, cycle hunt

    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_13_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
     menggunakan
    0.49
     გამოყენ
    0.49
     어떻게
    0.44
    骸
    0.44
    Figure
    0.43
    allery
    0.43
     제가
    0.43
    ustat
    0.43
     Figure
    0.43
     بحيث
    0.43
    POSITIVE LOGITS
     Chúng
    0.54
     Zweifel
    0.52
    вес
    0.51
    чни
    0.50
    }|=
    0.50
    Ju
    0.50
    خلص
    0.49
    IGHT
    0.49
    ماس
    0.49
    าที
    0.49
    Activations Density 0.020%

    No Known Activations