© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151772
    Prev
    Next
    INDEX
    Explanations

    v1.5

    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_23_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
    хів
    0.38
     reigning
    0.38
     sofort
    0.37
    setImage
    0.36
     棉
    0.36
     dangerously
    0.35
    റാ
    0.35
    পাত্র
    0.35
    ٹن
    0.34
     complej
    0.34
    POSITIVE LOGITS
    Reduce
    0.40
     Reduce
    0.39
     acert
    0.38
    σταν
    0.35
    UE
    0.35
    ahat
    0.35
    uding
    0.34
    ătur
    0.34
    相
    0.34
    UED
    0.34
    Activations Density 0.003%

    No Known Activations