© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16249
    Prev
    Next
    INDEX
    Explanations

    universities and academic institutions

    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
    pointA
    0.45
    にあ
    0.40
    Japan
    0.38
     دوس
    0.38
     monof
    0.38
    liğini
    0.37
     ווא
    0.37
    絊
    0.37
    AsUpIndicator
    0.36
    Trades
    0.36
    POSITIVE LOGITS
     Stanford
    0.68
     UCLA
    0.68
    Stanford
    0.58
     Dartmouth
    0.56
     Cornell
    0.55
     Vanderbilt
    0.52
     OSU
    0.52
     SEC
    0.52
     Clemson
    0.51
     TCU
    0.51
    Activations Density 0.028%

    No Known Activations