© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28267
    Prev
    Next
    INDEX
    Explanations

    section of

    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_10_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
     Polonia
    0.28
    isierung
    0.27
    cgColor
    0.26
    h
    0.26
     ры
    0.26
    ϡ
    0.26
    رير
    0.25
    وة
    0.25
     параметр
    0.25
     значения
    0.25
    POSITIVE LOGITS
    人士
    0.31
    は
    0.29
    Ī
    0.29
    ing
    0.29
    स
    0.28
    는
    0.27
    ING
    0.26
    ना
    0.26
    美
    0.25
    Α
    0.25
    Activations Density 0.021%

    No Known Activations