© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215479
    Prev
    Next
    INDEX
    Explanations

    emoticon representing smile and celebration

    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_5_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
    ت
    1.67
    ال
    1.55
    ל
    1.41
    lių
    1.38
    ন
    1.29
    る
    1.29
    س
    1.28
    us
    1.27
    ल्यू
    1.25
    न
    1.25
    POSITIVE LOGITS
    ’
    1.80
    that
    1.36
     that
    1.22
    ного
    1.13
    '
    1.08
    3
    0.98
     W
    0.92
    8
    0.92
    "
    0.91
     que
    0.91
    Activations Density 0.000%

    No Known Activations