© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155951
    Prev
    Next
    INDEX
    Explanations

    heavy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    एडा
    0.37
     Farn
    0.37
     disent
    0.36
     Eust
    0.36
    /');
    0.36
     kHz
    0.35
    ങ്കിലും
    0.35
     thin
    0.34
    軽量
    0.34
     zas
    0.34
    POSITIVE LOGITS
    Heavy
    2.19
     Heavy
    2.08
    重
    2.02
    heavy
    2.00
     heavy
    1.98
     тяже
    1.79
     heavier
    1.65
     重
    1.60
     heav
    1.59
     тяжё
    1.59
    Activations Density 0.001%

    No Known Activations