© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175803
    Prev
    Next
    INDEX
    Explanations

    alpha-2 adrenergic, Ctrl+Alt, log_var, μ

    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_20_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
    matmul
    0.30
    าที
    0.28
    稱為
    0.28
    小說
    0.28
     nosotros
    0.27
     اتارنا
    0.27
    ="@+
    0.27
    វេ
    0.27
     ምልክ
    0.27
    roll
    0.27
    POSITIVE LOGITS
     Tb
    0.34
     với
    0.31
     современном
    0.30
     Với
    0.29
     Paso
    0.29
    dois
    0.29
    
    0.29
    Với
    0.28
     Tm
    0.28
     Yellowstone
    0.28
    Activations Density 0.000%

    No Known Activations