© 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. 50601
    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
    ืด
    0.34
    ủy
    0.31
     აღმასრულებელი
    0.31
    ugal
    0.31
    amburger
    0.29
    ೆಯಿಂದ
    0.29
     uintptr
    0.29
    </tfoot>
    0.29
    avourites
    0.29
     toler
    0.28
    POSITIVE LOGITS
     Chili
    0.33
     কিলো
    0.31
     chili
    0.31
     sparked
    0.30
     இன
    0.30
    Dic
    0.30
     Kham
    0.30
     Chilli
    0.30
    ])/
    0.29
    tribe
    0.29
    Activations Density 0.000%

    No Known Activations