© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59923
    Prev
    Next
    INDEX
    Explanations

    Sufism

    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_2_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
    1.60
    ב
    1.23
    ED
    1.02
     of
    1.01
    in
    0.93
    ืน
    0.93
     εργ
    0.92
     On
    0.90
    </h5>
    0.90
     riches
    0.89
    POSITIVE LOGITS
    ри
    1.45
    ib
    1.41
    ون
    1.38
    ના
    1.38
    િ
    1.33
    _
    1.32
    o
    1.29
    ле
    1.27
    v
    1.27
    and
    1.25
    Activations Density 0.000%

    No Known Activations