© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84710
    Prev
    Next
    INDEX
    Explanations

    act as a

    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
    肐
    0.28
    itudini
    0.26
    傊
    0.26
    这种
    0.23
     ఎలాంటి
    0.23
    不存在
    0.23
    喟
    0.22
     दट
    0.22
     سيدنا
    0.22
    atism
    0.22
    POSITIVE LOGITS
     Gall
    0.25
    телем
    0.24
     visitors
    0.22
     美
    0.22
     customer
    0.22
     Vis
    0.22
     Parece
    0.22
     V
    0.22
     visite
    0.22
     mord
    0.22
    Activations Density 0.044%

    No Known Activations