© 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. 244269
    Prev
    Next
    INDEX
    Explanations

    initiating QApplication

    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
    Pm
    0.36
     साब
    0.36
    UtcNow
    0.33
     Pm
    0.33
    ી
    0.33
    弥
    0.32
    चीन
    0.32
     Plea
    0.32
    彌
    0.31
    そば
    0.31
    POSITIVE LOGITS
     vô
    0.38
     ہو۔
    0.37
     наука
    0.36
    avat
    0.35
     mesti
    0.35
    arakat
    0.35
    arian
    0.34
    auta
    0.34
     –
    0.34
    minster
    0.34
    Activations Density 0.000%

    No Known Activations