© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11639
    Prev
    Next
    INDEX
    Explanations

    milk and chocolate flavorings

    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_13_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
     punctatis
    0.50
    <unused1041>
    0.50
    <unused2014>
    0.50
    innerApiCalls
    0.50
     концерт
    0.49
    𓏸
    0.49
    舝
    0.49
    addAlignment
    0.48
     Maloney
    0.48
    ktional
    0.48
    POSITIVE LOGITS
     don
    0.52
     business
    0.49
    e
    0.48
     f
    0.48
     customer
    0.46
     steel
    0.46
     always
    0.45
     last
    0.45
    y
    0.45
     was
    0.44
    Activations Density 0.009%

    No Known Activations