© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26599
    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
    ب
    0.47
     Parnell
    0.44
    hets
    0.43
    ussie
    0.43
    pern
    0.42
    嚴
    0.42
    hat
    0.40
    ಲಾಗುತ್ತದೆ
    0.40
    embark
    0.40
    非常有
    0.40
    POSITIVE LOGITS
     pecc
    0.50
     offenders
    0.49
     lapses
    0.48
    ской
    0.48
    ﺪ
    0.47
     convicts
    0.46
     calves
    0.46
     osm
    0.46
     aquí
    0.46
     kelu
    0.46
    Activations Density 0.000%

    No Known Activations