© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199080
    Prev
    Next
    INDEX
    Explanations

    /usr/bin /usr/local/bin /usr/lib

    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_27_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
    ETC
    0.38
    鲅
    0.37
     ETC
    0.37
     seamlessly
    0.36
    雇用
    0.36
    嗦
    0.36
     cellophane
    0.36
     foremost
    0.35
    ैनिक
    0.34
    捪
    0.34
    POSITIVE LOGITS
    Non
    0.44
     Hot
    0.43
     Χ
    0.42
    CB
    0.39
    δ
    0.39
    cm
    0.37
     Non
    0.37
    дина
    0.37
    Σ
    0.37
    ih
    0.36
    Activations Density 0.001%

    No Known Activations