© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38303
    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_57_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
    тию
    0.39
    હા
    0.38
    त्ते
    0.35
     божомолдор
    0.35
    اهر
    0.34
    čkom
    0.34
    캣
    0.34
    istical
    0.34
    atenate
    0.34
    ẳ
    0.33
    POSITIVE LOGITS
    se
    0.52
     misschien
    0.44
     નહીં
    0.43
     vielleicht
    0.43
     විශේෂ
    0.42
     wikipedia
    0.42
     тысячи
    0.42
     todays
    0.42
     dipilih
    0.42
    seu
    0.42
    Activations Density 0.000%

    No Known Activations