© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218003
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units/quantities

    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
     stemming
    0.33
     ጋ
    0.32
     imbalances
    0.32
     precedence
    0.32
    BMP
    0.32
    ésére
    0.32
     непри
    0.31
     섹
    0.31
     HEL
    0.31
    颈
    0.30
    POSITIVE LOGITS
     umat
    0.37
    tenham
    0.34
     Blonde
    0.34
     NumPy
    0.34
     ساعت
    0.34
    ê
    0.34
     godziny
    0.33
    chiha
    0.33
     тонн
    0.33
     Tera
    0.33
    Activations Density 0.002%

    No Known Activations