© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4171
    Prev
    Next
    INDEX
    Explanations

    digits preceding units of measurement

    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_40_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
    <0xB3>
    0.40
    ാള
    0.37
     nine
    0.36
     ১১
    0.36
     ছত্র
    0.35
    meshgrid
    0.35
     seventeen
    0.35
    mechanical
    0.35
     ২৯
    0.35
    playground
    0.35
    POSITIVE LOGITS
    viii
    0.38
     VIII
    0.37
    VIII
    0.37
     посла
    0.37
    кну
    0.36
    ="../../../
    0.36
     outwards
    0.36
     xxl
    0.36
     quatre
    0.35
     अल्ट्रा
    0.35
    Activations Density 0.047%

    No Known Activations