© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158289
    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_2_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
    v
    0.92
     ',
    0.84
     ')
    0.80
     img
    0.75
     quadrato
    0.75
     (
    0.74
     intimidate
    0.73
     avem
    0.73
     אין
    0.73
     '\
    0.72
    POSITIVE LOGITS
    ে
    0.69
    حافظ
    0.66
    ómicos
    0.66
    น
    0.65
    ر
    0.64
    ut
    0.64
    τή
    0.63
    ad
    0.63
    ртов
    0.63
    нда
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.