© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    4. 99736
    Prev
    Next
    INDEX
    Explanations

    minute time slices

    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_16_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
    up
    0.58
    anda
    0.55
    were
    0.54
    weapons
    0.52
    become
    0.52
     Equipo
    0.51
    &
    0.50
    rese
    0.50
     Weapons
    0.50
    ld
    0.50
    POSITIVE LOGITS
    天气
    0.57
    气
    0.55
    Flights
    0.50
    |
    0.50
    傘
    0.49
    𝓎
    0.49
     ounces
    0.48
    েয়
    0.48
     छह
    0.48
    ้ำ
    0.47
    Activations Density 0.000%

    No Known Activations