© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208734
    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_25_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
     propiedad
    0.39
    
    0.38
    者に
    0.37
     décide
    0.36
    
    0.36
    浲
    0.36
     peligros
    0.36
    :_
    0.36
     किल
    0.35
    Cot
    0.35
    POSITIVE LOGITS
     ntawm
    0.38
     stumps
    0.37
    ￫
    0.37
    ensch
    0.35
    anska
    0.35
    របស់
    0.34
     조
    0.34
     PROCED
    0.34
     porówn
    0.33
     insecticides
    0.33
    Activations Density 0.000%

    No Known Activations