© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15904
    Prev
    Next
    INDEX
    Explanations

    sleep over narratives

    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_15_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
    前後
    0.52
     cifras
    0.51
    ボ
    0.50
     kó
    0.48
    ​]]
    0.47
    ਲੇ
    0.46
    六
    0.46
     consequências
    0.45
    些
    0.45
     Dés
    0.44
    POSITIVE LOGITS
     популя
    0.48
    führ
    0.48
    caa
    0.47
     отобра
    0.46
    avari
    0.45
     وبه
    0.45
     Samaj
    0.45
    ets
    0.45
    entry
    0.44
     använd
    0.44
    Activations Density 0.000%

    No Known Activations