© 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. 50482
    Prev
    Next
    INDEX
    Explanations

    ESL and FL certifications

    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
     Մ
    0.87
     オーバー
    0.86
     ﺍﻟ
    0.85
    ם
    0.84
     أكثر
    0.84
     Ар
    0.83
     מ
    0.82
     ৪
    0.82
     prema
    0.82
     ακ
    0.80
    POSITIVE LOGITS
    <0x80>
    0.95
    E
    0.89
    in
    0.82
    ans
    0.79
    <0x9B>
    0.74
    h
    0.74
    u
    0.72
    I
    0.70
    <0xA6>
    0.70
    <0xB4>
    0.63
    Activations Density 0.000%

    No Known Activations