© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165739
    Prev
    Next
    INDEX
    Explanations

    last

    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_31_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
     وقل
    0.40
     ९
    0.39
    यक
    0.38
     ಕಳೆದ
    0.38
    पिछले
    0.38
    vindos
    0.38
     gunpowder
    0.38
    र्तन
    0.38
     오늘은
    0.38
     सुधार
    0.37
    POSITIVE LOGITS
    Horizontal
    0.38
     혼
    0.35
    сток
    0.34
     کاس
    0.33
     Horizontal
    0.33
    ருங்க
    0.33
    暖
    0.33
    Cho
    0.32
    Points
    0.31
    ベート
    0.31
    Activations Density 0.001%

    No Known Activations