© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37304
    Prev
    Next
    INDEX
    Explanations

    1

    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_57_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
    monte
    0.42
    promise
    0.40
    )])
    0.40
    mongo
    0.40
    reement
    0.38
    MISSION
    0.38
    mits
    0.38
    ompok
    0.37
    mon
    0.37
    mission
    0.37
    POSITIVE LOGITS
     diel
    0.39
    laying
    0.38
    −
    0.38
    ests
    0.37
    埤
    0.37
     திக
    0.37
     Moves
    0.36
    机遇
    0.36
     Lay
    0.35
     EVAL
    0.35
    Activations Density 0.042%

    No Known Activations