© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2518
    Prev
    Next
    INDEX
    Explanations

    Yields: quantity

    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_40_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
     сет
    0.38
    ϒ
    0.38
    شب
    0.38
    ⾃
    0.37
    шек
    0.37
     ô
    0.37
     Cho
    0.36
    裾
    0.36
    听说
    0.35
    fords
    0.35
    POSITIVE LOGITS
     beso
    0.38
     Anal
    0.38
    Muc
    0.37
    arno
    0.37
    ణా
    0.37
    пами
    0.37
     muc
    0.37
    軽量
    0.37
    quear
    0.36
    mature
    0.36
    Activations Density 0.016%

    No Known Activations