© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89928
    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_23_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
     fb
    0.26
     overcome
    0.26
     minimize
    0.25
     अब
    0.25
    մբ
    0.24
    覤
    0.24
    ジア
    0.24
     ஏற
    0.24
     посте
    0.24
     பின்ன
    0.23
    POSITIVE LOGITS
    flight
    0.26
    unker
    0.25
     freighter
    0.24
    geber
    0.24
    फारिश
    0.24
    ypeł
    0.24
     Flight
    0.23
    ilarly
    0.23
    ocation
    0.23
    issait
    0.23
    Activations Density 0.019%

    No Known Activations