© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8987
    Prev
    Next
    INDEX
    Explanations

    coffee machine, pods, cleaning, intensity

    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_13_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
     retras
    0.55
    \%).
    0.52
     刺繍
    0.49
     dungeon
    0.48
     tranch
    0.47
     حس
    0.46
     učen
    0.46
    начально
    0.46
     барои
    0.46
     amulet
    0.46
    POSITIVE LOGITS
    EN
    0.55
    en
    0.55
    n
    0.55
    ..'
    0.54
    ept
    0.52
    Ops
    0.52
    ТО
    0.52
    nitz
    0.50
    рио
    0.49
     mở
    0.49
    Activations Density 0.014%

    No Known Activations