© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163662
    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_13_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
    -
    0.66
    0.65
     game
    0.55
     compliance
    0.54
     fateful
    0.53
     suspect
    0.52
     compilation
    0.50
    )
    0.50
     contraction
    0.49
     catalyst
    0.48
    POSITIVE LOGITS
    платы
    0.58
     جوړونک
    0.54
    SIDE
    0.53
     रिव्यू
    0.52
    屇
    0.52
     выпуска
    0.49
    lanan
    0.49
     있죠
    0.48
    мени
    0.48
    生素
    0.48
    Activations Density 0.000%

    No Known Activations