© 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. 105077
    Prev
    Next
    INDEX
    Explanations

    inequality

    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
    ن
    1.52
     to
    1.38
     and
    1.36
     have
    1.35
    ন
    1.34
     as
    1.23
    น
    1.23
     with
    1.20
    ল
    1.19
     at
    1.15
    POSITIVE LOGITS
    the
    0.97
    моби
    0.97
    но
    0.95
    и
    0.95
    ке
    0.93
     interstices
    0.92
    ни
    0.89
    atamente
    0.86
    ุ
    0.86
    ний
    0.85
    Activations Density 0.001%

    No Known Activations