© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36572
    Prev
    Next
    INDEX
    Explanations

    pure magic and luck

    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_3_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
    ت
    0.70
    You
    0.63
     You
    0.61
     cidad
    0.61
    त
    0.60
    ed
    0.59
    ال
    0.59
    н
    0.59
    고
    0.59
    ร
    0.58
    POSITIVE LOGITS
     खेल
    0.66
    0.62
     catégorie
    0.61
    argento
    0.60
    clarinet
    0.60
     CHEMISTRY
    0.56
     RX
    0.55
     peringkat
    0.55
     Matem
    0.55
     añadido
    0.55
    Activations Density 0.009%

    No Known Activations