© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79284
    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_31_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
    मति
    0.39
    Maxwell
    0.38
     pide
    0.38
    不如
    0.38
    fromUtf
    0.38
    🥹
    0.37
     поме
    0.36
    कीन
    0.35
    endor
    0.35
     Spiegel
    0.35
    POSITIVE LOGITS
     phosphoric
    0.39
     상세
    0.38
    闇
    0.38
     అంశ
    0.37
     squadron
    0.37
     ನಿಮಗೆ
    0.36
     思
    0.36
    楇
    0.36
    ಿಗಳ
    0.35
    らっしゃる
    0.35
    Activations Density 0.000%

    No Known Activations