© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82116
    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_0_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
    ing
    2.41
    u
    2.31
    o
    2.16
     that
    2.11
    ק
    2.00
    e
    1.90
    ة
    1.88
     with
    1.75
    er
    1.70
    ant
    1.67
    POSITIVE LOGITS
     I
    1.52
    )،
    1.37
    它
    1.22
     في
    1.16
     و
    1.14
    )。
    1.14
    看来
    1.10
     A
    1.04
     в
    1.04
     Š
    1.03
    Activations Density 0.000%

    No Known Activations