© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195706
    Prev
    Next
    INDEX
    Explanations

    #include and import

    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_26_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
     Recruiting
    0.36
     և
    0.34
     marred
    0.33
     થયો
    0.33
    qué
    0.32
     []:
    0.32
    ენტი
    0.32
    atti
    0.31
    ूब
    0.31
     shoes
    0.31
    POSITIVE LOGITS
    ษา
    0.36
     سکتی
    0.34
     writeFile
    0.32
     NS
    0.30
    emeen
    0.30
     tempHeader
    0.30
     создавать
    0.29
     Katy
    0.29
    ంబేద్కర్
    0.29
    憬
    0.29
    Activations Density 0.000%

    No Known Activations