© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210958
    Prev
    Next
    INDEX
    Explanations

    CPU and processor discussions

    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_20_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
     perros
    0.39
    āti
    0.38
     pants
    0.38
     cows
    0.36
     things
    0.36
     cinemas
    0.36
     कारों
    0.35
    ⚈
    0.35
     बनना
    0.35
     dancers
    0.34
    POSITIVE LOGITS
    stripped
    0.37
    স্পতিবার
    0.36
    communic
    0.32
    راہیم
    0.32
     لحاظ
    0.31
    lucent
    0.31
    expressed
    0.31
    io
    0.30
    HAL
    0.30
    вичай
    0.30
    Activations Density 0.004%

    No Known Activations