© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50834
    Prev
    Next
    INDEX
    Explanations

    non-standard text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    ObjectModel
    0.40
     HBase
    0.40
    ٹرز
    0.39
     בז
    0.34
    ஸல்
    0.34
     ज़
    0.34
    Handle
    0.33
     ਫ
    0.33
    พล
    0.33
     Gleich
    0.33
    POSITIVE LOGITS
    वीण
    0.43
     alojamiento
    0.41
    ۇ
    0.41
    ֻ
    0.40
    ாட்டு
    0.39
    ocyt
    0.38
    处的
    0.38
    ɪ
    0.37
     okol
    0.35
    ǯ
    0.35
    Activations Density 0.029%

    No Known Activations