© 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. 77385
    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
    šķ
    0.36
     factor
    0.36
    并
    0.36
     trillions
    0.35
    STRAINT
    0.33
    And
    0.33
    נים
    0.33
     Freddy
    0.33
    స
    0.33
     gerektiğini
    0.32
    POSITIVE LOGITS
    ಜು
    0.40
    income
    0.38
     توص
    0.37
    original
    0.36
    Income
    0.35
     pozw
    0.35
    json
    0.34
    ejs
    0.34
    曇
    0.34
     Directory
    0.33
    Activations Density 0.000%

    No Known Activations