© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6352
    Prev
    Next
    INDEX
    Explanations

    json structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     avvi
    0.28
    ષ્ટ
    0.27
    襞
    0.27
     centres
    0.26
     nephews
    0.26
     रोचक
    0.26
    蒿
    0.26
     ലേഖ
    0.25
    Wit
    0.25
     lohnt
    0.25
    POSITIVE LOGITS
    settings
    0.26
     Old
    0.26
     Benchmark
    0.26
    Answer
    0.25
    noop
    0.24
     append
    0.24
    蹦
    0.24
     nos
    0.24
    inherit
    0.24
     APPEND
    0.24
    Activations Density 0.162%

    No Known Activations