© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11796
    Prev
    Next
    INDEX
    Explanations

    Jewish deli and bakery items

    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_13_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
    William
    0.48
     персонала
    0.47
    C
    0.47
    order
    0.46
    land
    0.44
    𝗞
    0.44
    Cl
    0.42
    incorporated
    0.42
    eral
    0.42
    𝘾
    0.42
    POSITIVE LOGITS
     bagels
    0.72
     Shabbat
    0.72
     Jewish
    0.71
     Hebrew
    0.65
     Knesset
    0.61
     Jews
    0.61
     Passover
    0.59
     rabbis
    0.59
     Pesach
    0.59
     Talmud
    0.58
    Activations Density 0.034%

    No Known Activations