© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157446
    Prev
    Next
    INDEX
    Explanations

    Star

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    LookAndFeelInfo
    0.39
     vaginalis
    0.37
     Henrietta
    0.36
     Hepatitis
    0.35
     ஹெ
    0.35
     А
    0.34
     Herm
    0.34
     peanuts
    0.34
     Ме
    0.33
     ACS
    0.33
    POSITIVE LOGITS
     Star
    3.45
    Star
    3.41
     star
    3.19
    star
    3.00
     STAR
    3.00
    STAR
    2.83
    星
    2.80
     स्टार
    2.72
     স্টার
    2.59
    スター
    2.47
    Activations Density 0.001%

    No Known Activations