© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79507
    Prev
    Next
    INDEX
    Explanations

    what should I do

    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_31_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
    portion
    0.37
    嵌
    0.36
     dide
    0.35
    ад
    0.34
    тил
    0.34
    exc
    0.34
    悬
    0.33
     lulus
    0.33
     terdapat
    0.33
    懸
    0.32
    POSITIVE LOGITS
    Aut
    0.33
    하기
    0.32
     предназна
    0.32
    ^{*}$,
    0.32
     destinés
    0.32
    强势
    0.31
    기가
    0.31
     intended
    0.31
    MemoryWarning
    0.30
    시기
    0.30
    Activations Density 0.003%

    No Known Activations