© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108976
    Prev
    Next
    INDEX
    Explanations

    laughter sounds

    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_1_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
    s
    1.53
    ਆਂ
    1.19
    ς
    1.12
    ओं
    1.05
    ের
    1.02
    Ꮁ
    1.01
    νει
    1.00
    ों
    0.97
     производ
    0.97
     Ive
    0.93
    POSITIVE LOGITS
     t
    1.06
     was
    1.01
     is
    1.00
     que
    0.96
     ש
    0.95
     has
    0.94
     ي
    0.92
    at
    0.91
    it
    0.88
    ר
    0.88
    Activations Density 0.000%

    No Known Activations