© 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. 36719
    Prev
    Next
    INDEX
    Explanations

    construction industry and related topics

    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
    Correo
    0.52
     Schur
    0.50
    ᅯ
    0.49
    Abu
    0.48
    Blocks
    0.48
    Slides
    0.48
    ScrollBar
    0.48
    Bihar
    0.46
     Ах
    0.46
    Background
    0.45
    POSITIVE LOGITS
    ita
    0.57
    n
    0.55
    ne
    0.49
    р
    0.49
    न
    0.48
    ruction
    0.47
    ala
    0.47
    otor
    0.47
    r
    0.47
    ر
    0.47
    Activations Density 0.035%

    No Known Activations