© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52177
    Prev
    Next
    INDEX
    Explanations

    solutions are introduced

    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
     systematically
    0.39
     ku
    0.38
     Pampl
    0.37
     ফের
    0.35
     ([]
    0.35
     Ku
    0.35
    वेयर
    0.34
    ということで
    0.34
     ◆
    0.34
     gums
    0.34
    POSITIVE LOGITS
    ğun
    0.38
     Goals
    0.38
     ফটোগ্রাফ
    0.37
    狒
    0.37
     دام
    0.36
    笑着
    0.36
     عکس
    0.36
    楝
    0.36
     reductase
    0.35
     лаборатор
    0.35
    Activations Density 0.002%

    No Known Activations