© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146687
    Prev
    Next
    INDEX
    Explanations

    between

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Π
    0.39
    Ι
    0.39
     काउंसलिंग
    0.38
    Не
    0.38
    产生了
    0.38
     Became
    0.38
     रिक्वायरमेंट
    0.37
    Θ
    0.37
    arono
    0.37
     Вики
    0.36
    POSITIVE LOGITS
     entre
    0.66
     then
    0.61
     Entre
    0.55
    entre
    0.55
     between
    0.54
     entonces
    0.54
    Entre
    0.54
     mellan
    0.54
     između
    0.54
     antara
    0.53
    Activations Density 0.002%

    No Known Activations