© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178610
    Prev
    Next
    INDEX
    Explanations

    essential importance

    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_24_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
    आई
    0.40
    Р
    0.39
    ú
    0.38
    Нау
    0.37
     industria
    0.35
    ripción
    0.34
    uatu
    0.34
    个
    0.33
    доров
    0.33
    itiis
    0.33
    POSITIVE LOGITS
    ilere
    0.36
     clade
    0.36
     맡
    0.35
    身長
    0.35
    phrine
    0.34
     alent
    0.34
    割合
    0.34
     انقل
    0.33
     تساعد
    0.33
     slashing
    0.33
    Activations Density 0.006%

    No Known Activations