© 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. 206122
    Prev
    Next
    INDEX
    Explanations

    Muslims and Islam

    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
    Today
    0.49
     сегодня
    0.48
    过滤
    0.45
    taste
    0.44
    غ
    0.44
    today
    0.44
    Сегодня
    0.43
    Taste
    0.42
    地铁
    0.41
    Filtering
    0.40
    POSITIVE LOGITS
    ']),
    0.48
    ዠ
    0.46
     framed
    0.43
    '])
    0.43
     RM
    0.43
     नेम
    0.43
     ensue
    0.42
     Ll
    0.42
     Cs
    0.42
     CSM
    0.41
    Activations Density 0.000%

    No Known Activations