© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172302
    Prev
    Next
    INDEX
    Explanations

    stress testing

    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_20_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
     м
    0.41
    FontFace
    0.41
    Мі
    0.40
     infertility
    0.40
    Mons
    0.40
    alyse
    0.39
    َم
    0.39
    פע
    0.39
     شیع
    0.39
    苦手
    0.39
    POSITIVE LOGITS
     सीमित
    0.47
     quantitatively
    0.46
     limitado
    0.46
     limited
    0.46
     Limited
    0.46
     제한
    0.45
     galore
    0.45
     went
    0.44
     limitada
    0.43
     preservar
    0.43
    Activations Density 0.002%

    No Known Activations