© 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. 217738
    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
    尻
    0.39
    ണ്ടും
    0.38
    frontal
    0.36
    ologues
    0.35
    ക്കുകയും
    0.35
     monastery
    0.35
     kampus
    0.35
     호텔
    0.35
     luyện
    0.34
    PrivateRoute
    0.34
    POSITIVE LOGITS
     Gideon
    0.41
    অথ
    0.39
     Grover
    0.38
    畬
    0.36
     graus
    0.36
     Moritz
    0.34
     Dö
    0.34
     ?>
    0.34
     Wet
    0.34
     元
    0.34
    Activations Density 0.000%

    No Known Activations