© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217201
    Prev
    Next
    INDEX
    Explanations

    to be in

    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_16_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
     acyl
    0.49
    派遣
    0.49
    Unifier
    0.45
     writs
    0.45
    Dispatch
    0.45
    Writer
    0.44
    ๛
    0.44
     هاکي
    0.44
     hogares
    0.43
     kvůli
    0.43
    POSITIVE LOGITS
    kreuz
    0.51
    ক
    0.46
     trench
    0.45
    ersk
    0.43
    冇
    0.43
    stocks
    0.42
     myn
    0.41
     Bid
    0.40
    nač
    0.40
     rb
    0.40
    Activations Density 0.000%

    No Known Activations