© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3068
    Prev
    Next
    INDEX
    Explanations

    feeling overwhelming or intense 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_40_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
     toughness
    0.36
     suj
    0.35
     შეგი
    0.34
     Gefühl
    0.34
    꼬
    0.33
     tags
    0.33
     greatness
    0.32
     accumulations
    0.32
     calibrations
    0.32
    <0x07>
    0.31
    POSITIVE LOGITS
     horrified
    0.46
     delighted
    0.42
     terrified
    0.42
     embarrassed
    0.40
     desolate
    0.38
     appalled
    0.38
     miserable
    0.38
     furious
    0.38
     devastated
    0.37
     amazed
    0.37
    Activations Density 0.063%

    No Known Activations