© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213268
    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_5_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
    ма
    1.08
    -
    1.06
    ח
    0.95
    is
    0.94
     of
    0.90
    of
    0.89
    ේ
    0.89
    were
    0.87
    ی
    0.81
    ни
    0.80
    POSITIVE LOGITS
    W
    1.09
    Z
    1.05
    B
    1.00
    J
    1.00
    N
    0.98
    V
    0.96
    یک
    0.92
    H
    0.91
     Конечно
    0.91
    U
    0.91
    Activations Density 0.000%

    No Known Activations