© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2565
    Prev
    Next
    INDEX
    Explanations

    Postman

    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_38_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
    화
    0.46
     inscription
    0.40
     화
    0.40
    ন্ন
    0.39
     Adobe
    0.37
    溺
    0.37
    нения
    0.37
     Crack
    0.37
     merek
    0.37
    Application
    0.37
    POSITIVE LOGITS
    िसू
    0.41
    icho
    0.40
    unque
    0.39
    マス
    0.38
     Walden
    0.37
    rictional
    0.36
     Hinter
    0.36
     இயக்குநர்
    0.36
    𝗌
    0.36
     Muskel
    0.35
    Activations Density 0.002%

    No Known Activations