© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165606
    Prev
    Next
    INDEX
    Explanations

    baking

    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_31_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
     racetr
    0.34
     mist
    0.33
    supset
    0.32
    װ
    0.32
    ectable
    0.31
     Пока
    0.31
     տար
    0.31
     Charities
    0.30
     charities
    0.30
    rising
    0.30
    POSITIVE LOGITS
    ད་
    0.35
     Lào
    0.35
     자유
    0.35
     lệnh
    0.35
    犀
    0.35
    ıkları
    0.34
     প্রস্তাবে
    0.34
    しよう
    0.34
    rimazole
    0.33
     diretamente
    0.33
    Activations Density 0.002%

    No Known Activations