© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59674
    Prev
    Next
    INDEX
    Explanations

    PHP

    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
    六
    0.50
    ELLOW
    0.47
    POD
    0.44
    ٣
    0.43
    Six
    0.43
     छह
    0.42
    RX
    0.40
    SIX
    0.40
     여섯
    0.40
     الثالث
    0.39
    POSITIVE LOGITS
     php
    0.71
     eight
    0.70
     my
    0.69
    php
    0.65
    8
    0.65
     Eight
    0.64
     eighth
    0.62
     acht
    0.61
     PHP
    0.61
     eighty
    0.60
    Activations Density 0.001%

    No Known Activations