© 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. 9920
    Prev
    Next
    INDEX
    Explanations

    historical figures and events

    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
     late
    1.95
    late
    1.72
    Late
    1.70
     Late
    1.67
     दिवंगत
    1.41
     deceased
    1.27
    晚
    1.19
     مرحوم
    1.10
    deceased
    1.10
    늦
    1.05
    POSITIVE LOGITS
    ighe
    0.36
    tten
    0.36
     शुक्र
    0.36
    ித்த
    0.35
    重新
    0.35
     அவ்வ
    0.35
     exhaust
    0.34
    >');
    0.34
     reappear
    0.34
     powering
    0.34
    Activations Density 0.039%

    No Known Activations