© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131546
    Prev
    Next
    INDEX
    Explanations

    Aunt, Elijah, Corrientes

    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_1_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
    a
    1.85
    an
    1.44
    1.42
    ä
    1.37
    ik
    1.32
     was
    1.27
    é
    1.25
    ag
    1.20
    im
    1.19
    á
    1.16
    POSITIVE LOGITS
    徊
    1.02
    ري
    1.01
    I
    1.01
    ल
    1.01
    んで
    0.95
    らない
    0.95
    할
    0.94
    들이
    0.93
    нта
    0.93
    。",
    0.93
    Activations Density 0.000%

    No Known Activations