© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213181
    Prev
    Next
    INDEX
    Explanations

    Beverly Hills, beverage, Bevois

    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_5_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
    1.17
     in
    1.02
     mesmer
    0.99
    ON
    0.98
    ת
    0.95
     on
    0.95
    ם
    0.93
    म
    0.91
    מ
    0.91
     de
    0.90
    POSITIVE LOGITS
    ни
    1.49
    િ
    1.21
    ές
    1.14
    но
    1.12
    ке
    1.09
    3
    1.09
    ία
    1.06
    ls
    1.04
    ев
    1.03
    ית
    1.01
    Activations Density 0.000%

    No Known Activations