© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99207
    Prev
    Next
    INDEX
    Explanations

    act as a

    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_16_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
    ises
    0.35
    uell
    0.33
    ș
    0.33
    emaking
    0.32
    ét
    0.31
    ități
    0.31
    țion
    0.31
    тором
    0.30
    和他
    0.30
    ú
    0.30
    POSITIVE LOGITS
    ensical
    0.35
     `'\\
    0.34
     gcd
    0.33
    স্বাধীন
    0.33
    สามารถ
    0.33
    வையான
    0.33
    بعا
    0.33
     باشند
    0.32
     можуть
    0.32
    ابع
    0.32
    Activations Density 0.059%

    No Known Activations