© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29877
    Prev
    Next
    INDEX
    Explanations

    request with parameter 'for_'

    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
    uti
    0.44
    ucus
    0.41
    記録
    0.40
    wym
    0.40
     कुर्बानी
    0.39
    Ņ
    0.39
    ologii
    0.39
    Bast
    0.39
    ptic
    0.38
    чини
    0.38
    POSITIVE LOGITS
     mapView
    0.43
    机
    0.37
    찰
    0.37
     adoration
    0.36
    停止
    0.36
     immobilized
    0.35
     candlestick
    0.35
    жна
    0.34
     दिग्विजय
    0.34
    
    0.34
    Activations Density 0.000%

    No Known Activations