© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130232
    Prev
    Next
    INDEX
    Explanations

    PNG

    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_6_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
     أك
    1.21
     acht
    1.19
     过
    1.13
     Ви
    1.05
     内
    1.04
     Ли
    1.03
     مؤرشف
    1.02
     Při
    1.02
    '
    1.02
    ни
    1.02
    POSITIVE LOGITS
    ה
    1.12
    ט
    1.12
     viscosity
    1.03
    لی
    1.02
    ด
    0.98
     as
    0.95
    ریت
    0.93
     workbench
    0.91
     flange
    0.91
     metabolism
    0.90
    Activations Density 0.003%

    No Known Activations