© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130531
    Prev
    Next
    INDEX
    Explanations

    Latin language

    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
    1.17
    lık
    1.00
    y
    0.97
    newer
    0.94
    molecular
    0.91
    fiction
    0.90
    roff
    0.89
    handel
    0.88
    า
    0.87
    negative
    0.85
    POSITIVE LOGITS
    ین
    1.34
     for
    1.24
     on
    1.10
     to
    1.09
    ز
    1.06
    কে
    1.03
    ay
    1.00
    에
    0.98
    부
    0.97
     as
    0.97
    Activations Density 0.002%

    No Known Activations