© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100525
    Prev
    Next
    INDEX
    Explanations

    capital letter convention

    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_16_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
    ي
    0.54
    こんにちは
    0.48
    ずっと
    0.48
     ﺍ
    0.47
    𓏧
    0.46
     تھی
    0.46
     Maraton
    0.46
     amma
    0.46
     BuzzFeed
    0.46
     Himself
    0.45
    POSITIVE LOGITS
     firmness
    0.42
     мно
    0.42
     höchsten
    0.40
     главы
    0.38
    。
    0.38
     firm
    0.37
     toilet
    0.37
     perfect
    0.36
     matrix
    0.36
     rows
    0.36
    Activations Density 0.000%

    No Known Activations