© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230091
    Prev
    Next
    INDEX
    Explanations

    potholes

    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_6_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
    เป็น
    1.20
    我们
    1.10
    ᚕ
    0.98
    Лю
    0.93
    Ру
    0.91
    묭
    0.89
    ↵
    0.87
    Вот
    0.87
     Neend
    0.87
    dien
    0.86
    POSITIVE LOGITS
    il
    1.43
    ing
    1.23
    я
    1.09
    as
    1.04
    ad
    1.01
    0
    1.00
    ic
    0.98
     by
    0.98
     with
    0.97
    ed
    0.95
    Activations Density 0.000%

    No Known Activations