© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48830
    Prev
    Next
    INDEX
    Explanations

    building structures

    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_10_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
    0.52
    ↵
    0.47
    Grazie
    0.46
    리
    0.44
    ନ
    0.44
    п
    0.44
    те
    0.43
    មិន
    0.43
    ஷ
    0.43
    였
    0.42
    POSITIVE LOGITS
    ASTER
    0.44
    UD
    0.42
    ONSE
    0.41
    ⒏
    0.41
    AF
    0.41
    UN
    0.40
     স্থাপত্য
    0.40
    ÈRES
    0.40
     washable
    0.39
     Divisional
    0.39
    Activations Density 0.043%

    No Known Activations