© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12362
    Prev
    Next
    INDEX
    Explanations

    police, report, emergency, 911

    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_13_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
     灯
    0.50
    agar
    0.49
     αγ
    0.49
     қи
    0.48
     ask
    0.48
     tell
    0.48
     expand
    0.48
     identifying
    0.48
     bloom
    0.46
     agreements
    0.46
    POSITIVE LOGITS
    Н
    0.52
    انگ
    0.49
     thứ
    0.48
    Bạn
    0.47
     éste
    0.47
     policiais
    0.46
    此
    0.46
    城市
    0.46
     dát
    0.45
    警方
    0.44
    Activations Density 0.012%

    No Known Activations