© 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. 143779
    Prev
    Next
    INDEX
    Explanations

    USCIS

    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
    to
    1.91
    ו
    1.65
    ق
    1.53
    다
    1.45
    It
    1.43
    ta
    1.37
    c
    1.28
    u
    1.28
    tra
    1.25
    In
    1.24
    POSITIVE LOGITS
     for
    1.95
    ем
    1.52
    ipe
    1.41
    erne
    1.28
    elty
    1.27
    ن
    1.27
    ana
    1.26
     by
    1.22
    ă
    1.22
    не
    1.21
    Activations Density 0.000%

    No Known Activations