© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34906
    Prev
    Next
    INDEX
    Explanations

    Then there was introduction

    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_7_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
     vaccin
    0.31
    ﺩ
    0.29
    お客
    0.29
    ↵
    0.28
    东西
    0.27
    as
    0.26
    achricht
    0.26
     version
    0.25
     duplication
    0.25
     landscape
    0.25
    POSITIVE LOGITS
    ก็
    0.34
    ه
    0.33
    ு
    0.33
    ological
    0.32
    Pentru
    0.32
    ین
    0.32
    س
    0.32
    으로
    0.32
     erlaub
    0.31
    ि
    0.31
    Activations Density 0.001%

    No Known Activations