© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4362
    Prev
    Next
    INDEX
    Explanations

    health concerns or

    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
     marrón
    0.34
     коричне
    0.32
    adakan
    0.31
    |.|.|
    0.30
     nez
    0.29
    ForSettings
    0.29
    สัง
    0.29
    菘
    0.29
    ⢿
    0.29
    ส่วน
    0.29
    POSITIVE LOGITS
    agland
    0.33
     Administration
    0.32
    <0xDB>
    0.31
    érica
    0.29
    ﺓ
    0.29
     address
    0.29
    排行
    0.29
     tandem
    0.28
     EPA
    0.28
    uenti
    0.28
    Activations Density 0.002%

    No Known Activations