© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241720
    Prev
    Next
    INDEX
    Explanations

    html/css style properties

    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
     cow
    0.42
     설명
    0.38
    >/</
    0.37
     сочи
    0.37
     AUTO
    0.37
     pilot
    0.36
    姗
    0.36
    Auto
    0.36
     Auto
    0.36
     説明
    0.36
    POSITIVE LOGITS
    PluginResult
    0.40
    range
    0.39
     ciência
    0.37
    ())+
    0.37
     उन
    0.36
     Š
    0.36
     ड्रिल
    0.36
     blí
    0.36
    boundaries
    0.36
     boundaries
    0.36
    Activations Density 0.001%

    No Known Activations