© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211015
    Prev
    Next
    INDEX
    Explanations

    net or screen related to doors/hoods

    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_19_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
     ἐ
    0.47
     produite
    0.47
    มาจาก
    0.46
    HeaderAccept
    0.46
     ἀ
    0.44
    柔らか
    0.43
    AppBsky
    0.43
    ర్టు
    0.43
    帳
    0.43
     мисте
    0.42
    POSITIVE LOGITS
     smiling
    0.46
     largo
    0.46
    .,
    0.45
    <0x0D>
    0.43
    bians
    0.43
     Cheshire
    0.42
     Bia
    0.41
     ":
    0.41
     recognized
    0.41
    para
    0.41
    Activations Density 0.000%

    No Known Activations