© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63768
    Prev
    Next
    INDEX
    Explanations

    food blogs and recipe sites

    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_41_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
     Food
    0.46
    Food
    0.42
    challenged
    0.42
     naked
    0.42
    ۃ
    0.40
     Nig
    0.39
    Bobby
    0.38
     Bobby
    0.38
    exceptions
    0.38
    chall
    0.38
    POSITIVE LOGITS
     PhD
    0.44
    Conc
    0.40
     Dolan
    0.40
    PhD
    0.39
     Perrin
    0.39
     Birth
    0.38
    出生
    0.38
    cJ
    0.38
     ninth
    0.37
    \%,
    0.37
    Activations Density 0.000%

    No Known Activations