© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60938
    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_2_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
    '
    1.55
    ু
    1.30
     have
    1.20
     ensue
    1.08
    {\
    1.04
    이지만
    1.03
     on
    1.02
     seep
    1.02
     has
    0.98
     persist
    0.98
    POSITIVE LOGITS
    ation
    1.50
    م
    1.37
    ский
    1.20
    ado
    1.20
    ند
    1.16
    hs
    1.16
    t
    1.16
    nement
    1.11
    chloride
    1.09
    nen
    1.08
    Activations Density 0.000%

    No Known Activations