© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 144650
    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
     can
    1.51
    <0x0D>
    1.45
    aj
    1.35
     for
    1.31
     and
    1.23
     were
    1.21
     t
    1.20
    IJ
    1.19
    (
    1.17
    牥
    1.17
    POSITIVE LOGITS
    ו
    2.14
    خ
    1.75
    い
    1.49
    ά
    1.49
    ล
    1.48
    ים
    1.45
    l
    1.45
    ర్
    1.41
    ש
    1.41
    م
    1.41
    Activations Density 0.000%

    No Known Activations