© 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. 253412
    Prev
    Next
    INDEX
    Explanations

    say "4"

    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
    三百
    0.43
     laying
    0.42
    <unused40>
    0.41
     Prac
    0.39
     FO
    0.39
     forty
    0.39
     axb
    0.39
    ‌.
    0.39
     )),
    0.38
     trăm
    0.38
    POSITIVE LOGITS
    وه
    0.41
    Director
    0.40
    Received
    0.38
    वा
    0.37
    Stock
    0.37
    essen
    0.36
    Chooser
    0.36
    NH
    0.35
    Einstein
    0.35
    Invent
    0.35
    Activations Density 0.001%

    No Known Activations