© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45201
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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_22_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
     य
    0.41
     Privacy
    0.41
     speaker
    0.41
     privacy
    0.40
     Lx
    0.40
     SPEAKER
    0.39
     outlier
    0.39
     तेज़
    0.38
     *
    0.38
     SECUR
    0.37
    POSITIVE LOGITS
    aho
    0.40
     প্রকৃতপক্ষে
    0.39
     unavoid
    0.38
    sand
    0.37
     summits
    0.37
    ogas
    0.37
    форд
    0.37
     naturellement
    0.36
    グリップ
    0.36
    가격
    0.36
    Activations Density 0.003%

    No Known Activations