© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170613
    Prev
    Next
    INDEX
    Explanations

    codes and serial numbers

    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_20_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
     nhưng
    0.45
     fede
    0.44
     تضم
    0.43
    납
    0.42
    yor
    0.41
    лександр
    0.41
     entreprise
    0.41
    paypal
    0.40
    wbr
    0.40
     gặp
    0.40
    POSITIVE LOGITS
     versions
    0.44
     noticeable
    0.43
     도형
    0.42
     how
    0.41
     older
    0.40
     wavelengths
    0.40
     noticeably
    0.39
     Kuv
    0.39
     ຂ
    0.39
    Ticker
    0.38
    Activations Density 0.001%

    No Known Activations