© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36042
    Prev
    Next
    INDEX
    Explanations

    "..." structure

    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_11_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
     insuring
    0.35
    ]。
    0.32
     necessitating
    0.30
     neglecting
    0.30
     Τα
    0.29
    報導
    0.29
    toa
    0.28
    蟶
    0.28
    ArgumentParser
    0.28
    點
    0.28
    POSITIVE LOGITS
     Core
    0.31
     L
    0.30
    ри
    0.30
     Holy
    0.30
     Never
    0.30
     ([
    0.29
     symbol
    0.29
     Nav
    0.29
     daz
    0.29
    ون
    0.28
    Activations Density 0.305%

    No Known Activations