© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1681
    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_40_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
     foils
    0.42
    pyridazine
    0.39
    篂
    0.38
     জড়িত
    0.38
     በፊት
    0.38
    ibrated
    0.38
    fluoro
    0.37
    馴
    0.37
    foils
    0.36
     TVs
    0.36
    POSITIVE LOGITS
    Run
    0.54
     Run
    0.47
    Hand
    0.41
    run
    0.39
    Differential
    0.39
    AsUp
    0.39
    Rel
    0.38
    String
    0.38
    Suppose
    0.38
     profondément
    0.38
    Activations Density 0.000%

    No Known Activations