© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151085
    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_59_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
     sanctity
    0.36
     item
    0.35
    сні
    0.35
     curve
    0.34
     triumph
    0.33
    <0xDD>
    0.32
     must
    0.32
     table
    0.32
    hesized
    0.32
    γει
    0.32
    POSITIVE LOGITS
     міні
    0.61
     minimax
    0.59
    o
    0.59
     minh
    0.59
     MIN
    0.59
     Minh
    0.58
     مین
    0.58
     Min
    0.55
     Mino
    0.55
    Min
    0.54
    Activations Density 0.000%

    No Known Activations