© 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. 220073
    Prev
    Next
    INDEX
    Explanations

    (1-2) range

    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
     meas
    0.31
    ffi
    0.29
    สรร
    0.28
    قدر
    0.28
    ₅
    0.27
    elems
    0.27
     eğ
    0.27
     इत
    0.26
    պես
    0.26
     Paradox
    0.26
    POSITIVE LOGITS
    য়েক
    0.29
     ایسی
    0.29
    enzo
    0.28
    戀
    0.28
    மில்லை
    0.28
    および
    0.27
    Premium
    0.27
     இற
    0.27
     বলার
    0.27
    izowane
    0.27
    Activations Density 0.006%

    No Known Activations