© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145693
    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_0_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
    น
    1.71
    س
    1.46
    ۔
    1.45
    1.24
    。
    1.24
    ن
    1.21
     but
    1.16
     was
    1.14
    는
    1.14
    是
    1.13
    POSITIVE LOGITS
    i
    1.27
    ри
    1.20
    ী
    1.15
    ı
    1.13
     histoires
    1.12
    り
    1.10
     esfor
    1.05
     enseign
    1.05
    換え
    1.02
    institute
    1.02
    Activations Density 0.000%

    No Known Activations