© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201641
    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_37_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
     Huffman
    0.43
     Comité
    0.41
     Staying
    0.41
     Leach
    0.39
     Stay
    0.39
    珺
    0.38
     vandal
    0.38
    美术
    0.38
     Committees
    0.37
     Combustion
    0.37
    POSITIVE LOGITS
    liver
    0.42
     مختصر
    0.38
    انو
    0.37
     pur
    0.37
     своему
    0.36
    loglevel
    0.36
    ospheres
    0.36
    Victor
    0.35
    макра
    0.35
    降
    0.35
    Activations Density 0.000%

    No Known Activations