© 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. 9289
    Prev
    Next
    INDEX
    Explanations

    Scott, novels, train stations, pool, paddling

    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
    ré
    0.45
     three
    0.45
     delicious
    0.45
     of
    0.44
    naire
    0.44
    ží
    0.43
     waiter
    0.43
    é
    0.43
     sale
    0.43
     দি
    0.43
    POSITIVE LOGITS
    苯
    0.52
    ња
    0.49
    ામ
    0.49
    물을
    0.48
    スカート
    0.48
    Vk
    0.47
    莗
    0.46
    Burns
    0.46
    ᱧ
    0.45
    лга
    0.45
    Activations Density 0.005%

    No Known Activations