© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236829
    Prev
    Next
    INDEX
    Explanations

    screen bezels

    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_32_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
    BibitemShut
    0.42
     EZ
    0.42
     scont
    0.39
    Eggs
    0.38
    DIM
    0.37
    Пет
    0.37
    Grim
    0.37
    廾
    0.37
    GT
    0.37
    Mosaic
    0.36
    POSITIVE LOGITS
     ratio
    0.39
     fi
    0.38
    िफिशियल
    0.37
    十年
    0.36
     কার
    0.35
     Jordan
    0.35
    उचर
    0.35
     scar
    0.34
     মেয়ের
    0.34
     journeys
    0.34
    Activations Density 0.001%

    No Known Activations