© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234906
    Prev
    Next
    INDEX
    Explanations

    factory for creating test data

    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
    firing
    0.36
    馕
    0.36
     ওঠার
    0.35
    Ў
    0.34
     reared
    0.33
     digests
    0.33
    urbed
    0.33
     misinformation
    0.33
    cInfo
    0.32
     onwards
    0.32
    POSITIVE LOGITS
     Strong
    0.40
    斌
    0.38
     Festa
    0.38
     Benz
    0.37
     benz
    0.36
    Strong
    0.35
    Ссы
    0.35
    oxymethyl
    0.35
     ―
    0.35
     Kode
    0.35
    Activations Density 0.000%

    No Known Activations