© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78527
    Prev
    Next
    INDEX
    Explanations

    chest pain

    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_0_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
     the
    1.95
     on
    1.77
    ン
    1.67
    '
    1.44
    ن
    1.44
    T
    1.34
     of
    1.32
     is
    1.30
    S
    1.25
    ਮ
    1.24
    POSITIVE LOGITS
    các
    1.55
    g
    1.48
    cı
    1.38
    ли
    1.36
    ۰
    1.34
    ле
    1.27
    é
    1.27
    ^{*},
    1.26
    هاي
    1.26
    𝟎
    1.26
    Activations Density 0.001%

    No Known Activations