© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31202
    Prev
    Next
    INDEX
    Explanations

    library names

    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_31_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
     ‎
    0.28
     радиа
    0.28
     مرم
    0.27
    ﺗ
    0.27
    Pakistan
    0.26
     trabajan
    0.26
    ●
    0.26
     çalış
    0.25
     مليار
    0.25
     پاکستان
    0.25
    POSITIVE LOGITS
    urenc
    0.30
    腼
    0.28
    VENUE
    0.27
     उद्ध
    0.26
    ORTH
    0.25
    umphed
    0.25
    shims
    0.25
     пур
    0.25
     wooded
    0.25
    Turner
    0.24
    Activations Density 0.004%

    No Known Activations