© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234173
    Prev
    Next
    INDEX
    Explanations

    in 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_32_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
     structural
    0.42
     estructural
    0.41
     hopefully
    0.38
    ток
    0.38
     estrut
    0.38
     moisture
    0.37
     ز
    0.37
    東
    0.37
    <>
    0.36
     dehors
    0.36
    POSITIVE LOGITS
    üll
    0.38
    ▟
    0.38
    itei
    0.37
     Lạt
    0.36
    ogra
    0.35
    КТ
    0.34
     dukkh
    0.34
     कद
    0.34
    òn
    0.34
    ústria
    0.34
    Activations Density 0.001%

    No Known Activations