© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233013
    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_32_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
     misrepresented
    0.40
    ù
    0.40
    Ъ
    0.38
     والع
    0.38
     dared
    0.37
    Ù
    0.37
    ignée
    0.36
     ஸ்ப
    0.36
    ist
    0.35
     Um
    0.35
    POSITIVE LOGITS
    冭
    0.38
     Wett
    0.37
     तोड़
    0.37
     স্নাতক
    0.37
    GES
    0.37
    Gesch
    0.37
    莼
    0.37
    ravings
    0.36
    ιβ
    0.36
    equations
    0.35
    Activations Density 0.000%

    No Known Activations