© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50736
    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_10_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
    ار
    0.57
    ar
    0.57
    然
    0.50
    عا
    0.50
    ນ
    0.50
    ivia
    0.49
    𝟘
    0.48
    aría
    0.47
    ра
    0.47
    น
    0.46
    POSITIVE LOGITS
     ขอ
    0.50
     siger
    0.50
     escre
    0.49
     సు
    0.47
     frameN
    0.47
     Hace
    0.47
    ږ
    0.47
     rene
    0.46
     कौन
    0.46
     отре
    0.46
    Activations Density 0.000%

    No Known Activations