© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80897
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    gó
    1.40
    ール
    1.36
    ла
    1.35
    '
    1.34
    on
    1.27
    im
    1.27
    Ꮆ
    1.27
    ﺖ
    1.27
     noastră
    1.23
    ज
    1.22
    POSITIVE LOGITS
    that
    1.81
    ס
    1.56
    ่
    1.54
    ี
    1.49
    с
    1.41
    ۲
    1.22
    IL
    1.17
    을
    1.17
    O
    1.14
    ิ
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.