© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233343
    Prev
    Next
    INDEX
    Explanations

    categorized by complexity and effort

    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_32_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
     표현
    0.42
    الش
    0.40
     duckys
    0.37
     behavi
    0.37
     потен
    0.36
     নিষেধাজ্ঞ
    0.36
    !("{
    0.36
     cleanliness
    0.36
     محس
    0.35
    园
    0.35
    POSITIVE LOGITS
    窩
    0.41
     sede
    0.40
    飞行
    0.40
    flying
    0.40
     upscale
    0.37
    FDMA
    0.36
     flying
    0.36
    ครง
    0.36
     উড়ে
    0.36
     directamente
    0.35
    Activations Density 0.060%

    No Known Activations