© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103462
    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_1_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
    的
    1.63
     are
    1.61
    3
    1.58
    ED
    1.54
    س
    1.52
    7
    1.49
    .
    1.48
    4
    1.48
    在
    1.41
    6
    1.39
    POSITIVE LOGITS
    n
    1.52
    el
    1.41
    ת
    1.40
    is
    1.37
    ა
    1.34
    ۰
    1.31
    ०
    1.29
    provides
    1.27
    ר
    1.26
    il
    1.24
    Activations Density 0.000%

    No Known Activations