© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204600
    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_25_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
    nach
    0.50
    Ệ
    0.50
    nails
    0.49
    CH
    0.46
    Quel
    0.46
     ცხ
    0.46
     灬
    0.45
     SMITH
    0.45
     เฟ
    0.45
    Ế
    0.45
    POSITIVE LOGITS
     unimplemented
    0.42
     रवाना
    0.40
     rigid
    0.39
     всеми
    0.38
    行った
    0.38
     leyes
    0.37
     требований
    0.37
     tante
    0.36
    गिंग
    0.36
    出る
    0.36
    Activations Density 0.000%

    No Known Activations