© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44299
    Prev
    Next
    INDEX
    Explanations

    botnet creation/recruitment

    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_3_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
    et
    0.99
    i
    0.96
    t
    0.79
    v
    0.77
    väl
    0.73
    ta
    0.73
    st
    0.71
    ast
    0.71
    na
    0.68
    ä
    0.67
    POSITIVE LOGITS
    ल
    0.85
    ли
    0.83
    اك
    0.74
    λύ
    0.70
     glioma
    0.70
    もり
    0.70
    ادية
    0.68
    리
    0.67
    مد
    0.67
     vrijeme
    0.66
    Activations Density 0.000%

    No Known Activations