© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27044
    Prev
    Next
    INDEX
    Explanations

    31st

    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_10_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
    ↵
    0.21
     STARS
    0.18
     NE
    0.18
     нова
    0.18
     PBL
    0.17
     де
    0.17
     BWR
    0.17
     README
    0.17
     STAR
    0.17
    ння
    0.16
    POSITIVE LOGITS
    in
    0.27
    র
    0.22
    ères
    0.20
    as
    0.20
    ur
    0.19
    are
    0.19
    on
    0.19
    ers
    0.19
    ه‌های
    0.19
    দ
    0.18
    Activations Density 0.004%

    No Known Activations