© 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. 36689
    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_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
    ал
    0.88
    ка
    0.78
    are
    0.74
    твы
    0.68
    ről
    0.68
    ە
    0.68
    бе
    0.67
    masına
    0.66
    nehmens
    0.64
    lash
    0.63
    POSITIVE LOGITS
     of
    0.70
     in
    0.68
     niño
    0.64
     límite
    0.60
     fifth
    0.59
    ↵
    0.57
     OF
    0.57
     bailar
    0.57
     five
    0.56
     POD
    0.56
    Activations Density 0.000%

    No Known Activations