© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200371
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    zzles
    0.50
    еры
    0.46
    oric
    0.46
     pptn
    0.46
     viêm
    0.45
    v
    0.45
    лы
    0.44
     газа
    0.44
     flirting
    0.44
    m
    0.44
    POSITIVE LOGITS
     seller
    0.61
     Model
    0.54
     Bender
    0.52
    Ř
    0.52
    Seller
    0.50
     Надо
    0.50
     Seller
    0.50
     vendeur
    0.50
     MODEL
    0.49
     Modell
    0.49
    Activations Density 0.000%

    No Known Activations