© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 217008
    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
    ajn
    0.43
    termilk
    0.40
    amise
    0.40
    okens
    0.39
    aja
    0.38
    蒌
    0.38
    alk
    0.38
    জ্জামান
    0.38
    ancel
    0.37
    ateau
    0.36
    POSITIVE LOGITS
     heavy
    1.27
     Heavy
    1.27
    Heavy
    1.27
    heavy
    1.21
    重
    1.09
     heavier
    1.02
     ভারী
    0.95
     भारी
    0.92
     тяже
    0.92
     nặng
    0.92
    Activations Density 0.004%

    No Known Activations