© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170735
    Prev
    Next
    INDEX
    Explanations

    Re

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     re
    0.68
     Re
    0.49
    re
    0.49
     ре
    0.48
    Re
    0.47
     repl
    0.47
    repl
    0.45
    再
    0.44
    Place
    0.43
    w
    0.42
    POSITIVE LOGITS
     programmed
    0.53
     outfitted
    0.52
     parameterized
    0.50
     mentored
    0.50
     engineered
    0.49
     annotated
    0.49
     worded
    0.49
     configured
    0.48
    imated
    0.46
     encoded
    0.46
    Activations Density 0.001%

    No Known Activations