© 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. 44268
    Prev
    Next
    INDEX
    Explanations

    immutability and Python

    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
    Son
    0.58
    胭
    0.50
     yad
    0.49
    燔
    0.49
    सरा
    0.49
     adrenalin
    0.47
    dengan
    0.46
    大胆
    0.45
    Sono
    0.44
    स
    0.44
    POSITIVE LOGITS
    ки
    0.49
    style
    0.46
    ghi
    0.46
    ostream
    0.46
    stopped
    0.46
    ached
    0.45
    ButtonStyle
    0.45
    ASP
    0.44
    processable
    0.44
    uan
    0.44
    Activations Density 0.001%

    No Known Activations