© 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. 207245
    Prev
    Next
    INDEX
    Explanations

    disk-like structures

    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
     به‌
    0.51
     ？
    0.46
    geschoss
    0.44
    PointSize
    0.44
    $&$-
    0.44
     yếu
    0.44
    Frontend
    0.44
     ทํา
    0.43
    Symfony
    0.43
    ｵ
    0.43
    POSITIVE LOGITS
     pi
    0.50
    ppe
    0.50
     mogu
    0.49
    ğ
    0.47
    प्प
    0.45
     mulig
    0.45
     возмо
    0.45
     Pi
    0.45
    iran
    0.43
    ibile
    0.43
    Activations Density 0.000%

    No Known Activations