© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45469
    Prev
    Next
    INDEX
    Explanations

    tell a story or joke

    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_13_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
    多くの
    0.72
    ல்
    0.66
     નહીં
    0.61
     ľudí
    0.60
    К
    0.59
     oamenii
    0.57
    𝗷
    0.56
    㜌
    0.56
     serveur
    0.55
     lidí
    0.55
    POSITIVE LOGITS
     appreciating
    0.57
     appreciation
    0.56
    ed
    0.55
    oning
    0.52
    anst
    0.51
    appré
    0.51
    uous
    0.48
    简洁
    0.48
     उत्तम
    0.47
     दृष्टिकोण
    0.47
    Activations Density 0.052%

    No Known Activations