© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6412
    Prev
    Next
    INDEX
    Explanations

    psychological, emotional, biological, political impact

    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_39_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
    potentially
    0.36
     Nxh
    0.34
     fontos
    0.34
     Zam
    0.34
     MAY
    0.33
     хло
    0.33
    KEN
    0.32
     (-)
    0.32
     potentially
    0.32
    ことは
    0.31
    POSITIVE LOGITS
    FLP
    0.43
     автоматы
    0.42
     upl
    0.40
     metastability
    0.39
     matchList
    0.39
     juncture
    0.38
     হেড
    0.38
     للمع
    0.37
     दीजिएगा
    0.37
    啟用
    0.37
    Activations Density 0.215%

    No Known Activations