© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37059
    Prev
    Next
    INDEX
    Explanations

    . : ** * es ed ,

    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_11_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
    ed
    0.29
    äk
    0.28
    ी
    0.26
    ad
    0.25
    ke
    0.25
    ON
    0.25
    kan
    0.25
    nut
    0.25
    ot
    0.25
    Sk
    0.25
    POSITIVE LOGITS
     mesmos
    0.30
    пенди
    0.28
     silam
    0.28
     heureux
    0.27
    و
    0.27
     anglais
    0.27
     EXEMPL
    0.27
     achats
    0.27
     unha
    0.27
     Yatha
    0.27
    Activations Density 0.002%

    No Known Activations