© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37727
    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_3_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
    י
    0.98
    יות
    0.98
    il
    0.93
    ي
    0.91
    ان
    0.91
    ли
    0.90
    ;
    0.90
    ie
    0.89
    ні
    0.89
    ে
    0.88
    POSITIVE LOGITS
    d
    0.93
    š
    0.86
    ಂಕ್
    0.84
    𝔻
    0.84
    𝕥
    0.82
    ஜ்
    0.80
     ROW
    0.80
    서
    0.80
    ール
    0.80
     YEARS
    0.78
    Activations Density 0.000%

    No Known Activations