© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193855
    Prev
    Next
    INDEX
    Explanations

    more than half, less than half

    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_4_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
    in
    0.97
     are
    0.91
    _
    0.81
     factura
    0.79
    s
    0.79
     in
    0.77
     cuales
    0.74
     =
    0.74
     do
    0.73
    ine
    0.72
    POSITIVE LOGITS
    ال
    1.21
    ী
    1.19
    트
    1.14
    मा
    1.13
    ર
    1.09
    મ
    1.08
    ку
    1.07
    정
    1.02
    লা
    1.02
    تے
    1.01
    Activations Density 0.000%

    No Known Activations