© 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. 206564
    Prev
    Next
    INDEX
    Explanations

    web application development and security

    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
    !"));
    0.46
    ！
    0.46
    ！”
    0.45
     Communicate
    0.43
    ！）
    0.43
    拡散
    0.42
     পশু
    0.42
    inales
    0.42
     प्रॉपर्टी
    0.41
    阅读
    0.41
    POSITIVE LOGITS
    cei
    0.50
    sø
    0.44
    বারেই
    0.42
     Seasonal
    0.40
    Seasonal
    0.40
    ڼ
    0.40
     czter
    0.40
     heinous
    0.40
     eigenvalues
    0.39
     annuel
    0.39
    Activations Density 0.003%

    No Known Activations