© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 218061
    Prev
    Next
    INDEX
    Explanations

    flying and swimming

    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
     провин
    0.46
     scho
    0.42
    tax
    0.42
     tax
    0.40
    豳
    0.40
    cle
    0.39
     Tax
    0.39
    തീ
    0.38
    Tax
    0.38
    трите
    0.37
    POSITIVE LOGITS
     कुर्
    0.39
     AGAIN
    0.37
    ுண்டு
    0.37
     दुर्गा
    0.36
    Crunch
    0.35
    🕴
    0.35
     Organic
    0.34
     Officers
    0.34
     Kush
    0.34
     inoxidable
    0.34
    Activations Density 0.007%

    No Known Activations