© 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. 75387
    Prev
    Next
    INDEX
    Explanations

    Flows and unfolds

    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
    估
    0.38
    ebi
    0.36
    ctu
    0.35
    ंब
    0.35
    老年
    0.34
     puna
    0.34
    ണ്ട
    0.34
     Prado
    0.34
    uther
    0.33
    جی
    0.33
    POSITIVE LOGITS
    ALWAYS
    0.38
     :::
    0.37
    lemy
    0.35
    ϒ
    0.35
     COE
    0.34
    Pom
    0.33
    FORCE
    0.33
    CATS
    0.33
    challeng
    0.32
     cascades
    0.32
    Activations Density 0.038%

    No Known Activations