© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193927
    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_4_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
    setRoi
    0.48
    ண
    0.48
    rau
    0.48
    assemble
    0.47
    roni
    0.44
    checked
    0.44
    ীদের
    0.43
    पणे
    0.43
    provides
    0.42
    outline
    0.42
    POSITIVE LOGITS
     sensual
    0.55
     Kaya
    0.52
     intuit
    0.51
     égal
    0.50
     ойнотуу
    0.50
    巍
    0.50
     Inhalte
    0.49
     Somewhere
    0.49
     Už
    0.48
    yue
    0.48
    Activations Density 0.000%

    No Known Activations