© 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. 134085
    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
    of
    0.95
    "
    0.93
    '
    0.87
    1
    0.86
    aren
    0.84
    än
    0.82
    ”
    0.78
    agen
    0.76
     å
    0.76
    arente
    0.76
    POSITIVE LOGITS
    at
    1.12
    yı
    0.99
    твори
    0.99
    פ
    0.96
    ну
    0.95
    ุ
    0.95
    ת
    0.94
    میر
    0.93
    ா
    0.91
    로
    0.90
    Activations Density 0.000%

    No Known Activations