© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197903
    Prev
    Next
    INDEX
    Explanations

    mixed language

    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
     Gris
    0.44
    Prop
    0.41
    воль
    0.39
    邯
    0.38
     Prop
    0.38
     `=`
    0.38
    נת
    0.37
    ल्हा
    0.37
    Lunar
    0.35
     pod
    0.35
    POSITIVE LOGITS
     свя
    0.42
     কেন্দ্রের
    0.41
    vero
    0.40
     വൈ
    0.40
    uffer
    0.40
     육
    0.39
     Varn
    0.39
    ствует
    0.38
     Rosemary
    0.38
    ጹ
    0.38
    Activations Density 0.000%

    No Known Activations