© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48933
    Prev
    Next
    INDEX
    Explanations

    outrage and strong negative emotions

    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_10_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
    Л
    0.35
    НК
    0.33
    ل
    0.33
     arsen
    0.31
    ΙΚ
    0.29
    ä
    0.29
     آئی
    0.28
    述
    0.28
    ిల్లా
    0.28
    सुर
    0.28
    POSITIVE LOGITS
    ')
    0.30
     செலு
    0.29
    ’)
    0.29
    0
    0.27
    {
    0.27
    an
    0.26
     که
    0.26
    代わりに
    0.26
     التي
    0.26
    ھے
    0.26
    Activations Density 0.068%

    No Known Activations