© 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. 215566
    Prev
    Next
    INDEX
    Explanations

    two

    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
    each
    0.43
     each
    0.43
    "<<
    0.41
     każdej
    0.41
     каждый
    0.39
     प्रत्येक
    0.39
     каждой
    0.38
    貨
    0.38
     Каждый
    0.37
    asey
    0.36
    POSITIVE LOGITS
     terza
    0.39
    Duplicates
    0.38
     seus
    0.38
    자들이
    0.37
    cutta
    0.35
    Dup
    0.35
     Off
    0.35
    uenza
    0.35
    ⲟ
    0.34
     clara
    0.34
    Activations Density 0.002%

    No Known Activations