© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32659
    Prev
    Next
    INDEX
    Explanations

    gin

    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_50_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
    েকে
    0.38
    bbox
    0.37
    водитель
    0.35
     James
    0.34
    ｗ
    0.34
     caixa
    0.34
    тории
    0.34
    Glasses
    0.34
    торию
    0.34
    ümler
    0.33
    POSITIVE LOGITS
    gin
    0.38
     Хабаров
    0.38
    传
    0.38
    伝
    0.37
    GIN
    0.36
     تاب
    0.36
    CZ
    0.34
    古
    0.34
    МИ
    0.34
    itania
    0.34
    Activations Density 0.005%

    No Known Activations