© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215073
    Prev
    Next
    INDEX
    Explanations

    callbacks

    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
    ↵
    1.21
    د
    0.93
    ர்
    0.90
    ,
    0.89
     a
    0.86
    pl
    0.85
    り
    0.85
     as
    0.83
    نا
    0.82
    il
    0.82
    POSITIVE LOGITS
    И
    1.30
    ات
    1.16
     It
    1.13
    কে
    1.05
    오
    1.05
    รับ
    1.04
    కు
    1.04
    ก็
    1.04
    С
    1.04
    ב
    1.04
    Activations Density 0.000%

    No Known Activations