© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194481
    Prev
    Next
    INDEX
    Explanations

    wheelchair accessibility

    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_4_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
    <0x0D>
    1.02
    ش
    0.88
    ار
    0.79
    ？
    0.78
    라
    0.75
    রহ
    0.74
    다
    0.72
    نا
    0.69
    ↵↵
    0.68
    ا
    0.68
    POSITIVE LOGITS
     ו
    0.89
     ټ
    0.81
     και
    0.76
     է
    0.75
     Τ
    0.75
    g
    0.74
     ώ
    0.72
     Щ
    0.71
     ନ
    0.70
    dioxide
    0.70
    Activations Density 0.000%

    No Known Activations