© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31907
    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
     مكت
    0.39
    राना
    0.38
    ifest
    0.38
     writers
    0.38
    UserInput
    0.38
     ग्राहक
    0.37
     गरिएको
    0.37
    ʛ
    0.37
     historically
    0.36
     เขียน
    0.36
    POSITIVE LOGITS
    Supreme
    0.42
    Quan
    0.40
    Obviously
    0.39
    ත්ත
    0.37
     Ols
    0.36
     fud
    0.36
    اید
    0.36
     Obviously
    0.34
    Seeing
    0.34
     pode
    0.33
    Activations Density 0.000%

    No Known Activations