© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4892
    Prev
    Next
    INDEX
    Explanations

    world peace, war, watch, police

    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_38_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
     posteriorly
    0.40
    되
    0.36
    澎
    0.36
     persu
    0.35
    ès
    0.35
     separable
    0.34
     இடத்தை
    0.34
    될
    0.34
    嗕
    0.34
    smallskip
    0.33
    POSITIVE LOGITS
    Wide
    0.66
    WIDE
    0.64
     wide
    0.61
     Wide
    0.60
    wide
    0.53
    widet
    0.52
    Famous
    0.50
    各国
    0.49
    वाइड
    0.48
    renowned
    0.48
    Activations Density 0.087%

    No Known Activations