© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1153
    Prev
    Next
    INDEX
    Explanations

    test_size=0.2

    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_40_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
    ड्रीम
    0.40
    レビ
    0.38
     ট্যাব
    0.37
     వ్యక్
    0.37
     відста
    0.37
    톈
    0.35
     CDB
    0.35
    人心
    0.35
    setVertical
    0.35
     වශයෙන්
    0.35
    POSITIVE LOGITS
     dir
    0.40
     Oahu
    0.39
    ठमा
    0.38
    optimal
    0.37
    rotto
    0.37
     bagging
    0.37
    jot
    0.36
    DIR
    0.36
    ᵢ
    0.36
    Should
    0.36
    Activations Density 0.001%

    No Known Activations