© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6569
    Prev
    Next
    INDEX
    Explanations

    required skills

    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_39_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
     veterin
    0.41
    老大
    0.38
     nurs
    0.38
    トリック
    0.37
     സെക്രട്ട
    0.37
     সেটি
    0.36
    styling
    0.36
    固
    0.35
    ₵
    0.35
     بکر
    0.35
    POSITIVE LOGITS
    衮
    0.41
     Math
    0.41
    广泛
    0.40
     Compre
    0.40
    istory
    0.39
     কম্পিউটার
    0.39
     Encoding
    0.38
     컴퓨터
    0.38
     Proper
    0.38
    渙
    0.38
    Activations Density 0.029%

    No Known Activations