© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157603
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ம்
    1.02
    یر
    1.02
     as
    0.97
    '
    0.93
    ov
    0.89
    ot
    0.89
    いです
    0.87
     historian
    0.86
    ം
    0.86
     for
    0.85
    POSITIVE LOGITS
    ية
    1.96
    in
    1.76
    ر
    1.66
    在
    1.65
    ان
    1.61
    ال
    1.48
    ב
    1.45
    في
    1.34
    个
    1.32
    ৬
    1.31
    Activations Density 0.000%

    No Known Activations