© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92041
    Prev
    Next
    INDEX
    Explanations

    heavy metal contamination

    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_11_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
     botão
    0.50
     கற்ற
    0.50
     aprendido
    0.50
     GNU
    0.50
     religioso
    0.48
    <unused713>
    0.48
     religiosa
    0.47
    '।
    0.47
    ίζουν
    0.47
     दाल
    0.46
    POSITIVE LOGITS
     l
    0.56
    Т
    0.56
    sta
    0.55
     robberies
    0.54
     theft
    0.53
    2
    0.53
     n
    0.50
    ทะเล
    0.50
    j
    0.50
    factor
    0.49
    Activations Density 0.016%

    No Known Activations