© 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. 46177
    Prev
    Next
    INDEX
    Explanations

    .then(response => { console

    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_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
    ни
    0.82
    ﻜ
    0.81
    ﻴ
    0.81
    ﺘ
    0.78
     byli
    0.76
    ني
    0.74
    ليا
    0.74
    ﻠ
    0.74
    ട്ട
    0.73
    ﻨ
    0.70
    POSITIVE LOGITS
    t
    1.19
     It
    1.09
    ।
    1.06
    n
    1.02
    ت
    0.92
    is
    0.90
    r
    0.87
    ü
    0.87
    y
    0.86
    ii
    0.85
    Activations Density 0.014%

    No Known Activations