© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81036
    Prev
    Next
    INDEX
    Explanations

    surprise and mild frustration exclamations

    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_0_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
    .
    0.78
    -
    0.70
    ick
    0.60
    vention
    0.59
    art
    0.58
    3
    0.56
     breather
    0.55
    5
    0.55
    ur
    0.55
    4
    0.55
    POSITIVE LOGITS
    ف
    1.05
    s
    0.93
    ر
    0.80
    ب
    0.80
    t
    0.77
    től
    0.75
    د
    0.71
    tl
    0.70
     SLAs
    0.69
    tól
    0.68
    Activations Density 0.010%

    No Known Activations