© 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. 6588
    Prev
    Next
    INDEX
    Explanations

    endangered or threat

    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
    انو
    0.38
    Detect
    0.36
    佷
    0.36
     sharpen
    0.34
    ็ต
    0.34
     لع
    0.34
    StartPosition
    0.33
     పాఠ
    0.33
    哩
    0.33
    MinWidth
    0.33
    POSITIVE LOGITS
     threatened
    1.93
     endangered
    1.85
     Threatened
    1.63
     zagro
    1.62
     endanger
    1.58
     खतरे
    1.58
     jeopardy
    1.55
    threat
    1.52
     danger
    1.48
     amea
    1.48
    Activations Density 0.113%

    No Known Activations