© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29174
    Prev
    Next
    INDEX
    Explanations

    quoting or ending phrases

    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
    amentul
    0.38
    란
    0.36
    gelijk
    0.34
     Schall
    0.33
    )-$
    0.33
    enumi
    0.32
    oughs
    0.32
    黄色
    0.32
     bleue
    0.31
    rium
    0.31
    POSITIVE LOGITS
    钊
    0.41
    ይም
    0.39
    depression
    0.39
     गोस्वामी
    0.39
     Padua
    0.38
    癬
    0.38
    SubDirectory
    0.38
    공
    0.38
     itinéraires
    0.38
     Polytechnic
    0.38
    Activations Density 0.411%

    No Known Activations