© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209033
    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_10_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
    ద్ద
    0.58
    In
    0.51
    在
    0.50
    Operand
    0.49
    Neighbor
    0.48
    ilians
    0.48
    ían
    0.46
    Ashley
    0.45
    در
    0.45
    Leading
    0.45
    POSITIVE LOGITS
     හැකිය
    0.60
    𝒔
    0.50
     सम्
    0.49
     ски
    0.48
     slaying
    0.48
     Dynamics
    0.47
    ernet
    0.47
     सभ्यता
    0.46
     ໜ
    0.46
    freiheit
    0.46
    Activations Density 0.000%

    No Known Activations