© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 62
    Prev
    Next
    INDEX
    Explanations

    job titles

    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_40_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
     ara
    0.41
    Kami
    0.40
    kami
    0.39
    Diamond
    0.37
    hani
    0.37
    ětí
    0.36
    hag
    0.36
    ゥ
    0.36
    Ethan
    0.36
     الْ
    0.35
    POSITIVE LOGITS
     Businesses
    0.42
     곱
    0.41
     Gewinn
    0.40
     Pad
    0.38
     Milton
    0.38
     schme
    0.38
     México
    0.38
     LI
    0.36
     baos
    0.36
     cuanto
    0.35
    Activations Density 0.022%

    No Known Activations