© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139220
    Prev
    Next
    INDEX
    Explanations

    a thing

    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_12_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
    ᔾ
    0.33
    ంబేద్
    0.31
    ⱨ
    0.31
     assegn
    0.31
     striées
    0.31
     MPP
    0.31
     প্রভাস
    0.30
     হেফাজতে
    0.30
     RCLCPP
    0.30
    هایی
    0.29
    POSITIVE LOGITS
     .
    0.45
    e
    0.42
    ك
    0.40
    q
    0.37
    ening
    0.36
    5
    0.36
    内
    0.36
    ky
    0.35
    3
    0.34
     no
    0.33
    Activations Density 0.003%

    No Known Activations