© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50754
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ।
    0.50
    ಇ
    0.49
     regions
    0.48
    LO
    0.47
    揚げ
    0.46
    За
    0.46
     ribosomes
    0.46
     fossils
    0.46
    IQ
    0.46
    Ig
    0.45
    POSITIVE LOGITS
    𝕠
    0.53
    ớp
    0.49
    ős
    0.49
     kullanılır
    0.48
    ្ត
    0.48
    æss
    0.47
    虺
    0.47
     składa
    0.47
    acariy
    0.47
    veriş
    0.46
    Activations Density 0.000%

    No Known Activations