© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176339
    Prev
    Next
    INDEX
    Explanations

    `<head>` tag in HTML

    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_20_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
     无
    0.30
     It
    0.29
     says
    0.29
     ဖြစ်
    0.29
     হয়
    0.29
     আদেশ
    0.29
    Ｏ
    0.29
     But
    0.28
     有
    0.28
     يجب
    0.27
    POSITIVE LOGITS
     analysing
    0.34
    ્ટ
    0.32
     analisis
    0.31
     analizar
    0.31
     EURO
    0.31
     appartement
    0.31
    टाम
    0.30
     conhecer
    0.30
     averiguar
    0.30
     histograms
    0.29
    Activations Density 0.000%

    No Known Activations