© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5462
    Prev
    Next
    INDEX
    Explanations

    breaking down causes

    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_38_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
     ∑
    0.75
    sum
    0.69
     sum
    0.67
    ∑
    0.65
     Sum
    0.62
    ∏
    0.60
    Sum
    0.59
    reduce
    0.58
     reduce
    0.57
     Σ
    0.55
    POSITIVE LOGITS
     FRG
    0.47
     Divisions
    0.40
     longs
    0.39
     divisions
    0.38
     apples
    0.38
     arteries
    0.38
     carrots
    0.37
     स्टोक्स
    0.37
     bridal
    0.36
     Brides
    0.36
    Activations Density 0.043%

    No Known Activations