© 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. 79773
    Prev
    Next
    INDEX
    Explanations

    package main

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ੰਜ
    0.39
    asign
    0.39
    応
    0.37
    둠
    0.37
    媚
    0.36
    converter
    0.36
     converted
    0.35
    channels
    0.34
     Channels
    0.34
    mls
    0.34
    POSITIVE LOGITS
     prescriptive
    0.39
     CORPORATION
    0.38
    Corpor
    0.38
     Op
    0.37
     !==
    0.37
    点セット
    0.36
     eastbound
    0.36
     xas
    0.35
     Corporation
    0.35
     menu
    0.35
    Activations Density 0.000%

    No Known Activations