© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10724
    Prev
    Next
    INDEX
    Explanations

    jet engines, COM ports, serial communication

    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_13_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
    ↵
    0.33
     поли
    0.32
     fishermen
    0.30
     polych
    0.30
     Patriarch
    0.29
     prv
    0.29
     Stories
    0.29
     Palmyra
    0.28
     Vik
    0.28
    🏝
    0.28
    POSITIVE LOGITS
    俐
    0.29
    çin
    0.29
    rors
    0.29
    꾿
    0.28
    ptic
    0.27
     இங்கே
    0.27
    getBlue
    0.27
    膿
    0.27
    pus
    0.27
    直し
    0.27
    Activations Density 0.019%

    No Known Activations