© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19026
    Prev
    Next
    INDEX
    Explanations

    sack or storm

    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_15_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
    ),
    0.63
    AG
    0.63
    ad
    0.62
    RI
    0.60
    UL
    0.59
    onk
    0.59
    );
    0.57
    anst
    0.57
    含む
    0.57
    es
    0.57
    POSITIVE LOGITS
     Snacks
    0.57
    ುತ್ತಿದ್ದ
    0.51
     száz
    0.50
     comedor
    0.50
    ้ำ
    0.48
     Ankara
    0.48
     surged
    0.47
     Sticks
    0.47
     snacks
    0.47
    홈
    0.47
    Activations Density 0.001%

    No Known Activations