© 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. 153188
    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
    夰
    0.49
    KHTML
    0.49
     squarely
    0.48
    ByMerging
    0.46
     আপন
    0.46
     миру
    0.46
     awakened
    0.44
     окончания
    0.43
    apag
    0.43
    maxn
    0.43
    POSITIVE LOGITS
    ar
    0.57
    for
    0.54
     business
    0.52
    э
    0.52
     for
    0.49
     Business
    0.49
     variety
    0.48
     coaching
    0.48
     For
    0.47
     pump
    0.46
    Activations Density 0.000%

    No Known Activations