© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129703
    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_6_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
    ur
    1.41
    as
    1.16
    ado
    1.04
    ва
    1.02
    er
    0.97
    tive
    0.94
    ر
    0.94
    سازی
    0.89
    attu
    0.89
    v
    0.87
    POSITIVE LOGITS
     إ
    1.02
     empêcher
    0.99
     américains
    0.95
     أش
    0.94
     exámenes
    0.93
    Number
    0.93
     épars
    0.92
    実施
    0.91
     czas
    0.90
    на
    0.89
    Activations Density 0.000%

    No Known Activations