© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99768
    Prev
    Next
    INDEX
    Explanations

    secret laboratory

    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_16_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
    ي
    0.58
    ס
    0.56
     смотре
    0.52
    icrous
    0.50
    ্ণ
    0.49
    𝖗
    0.48
    findings
    0.47
    捭
    0.47
    ск
    0.47
     やつ
    0.46
    POSITIVE LOGITS
    êmica
    0.44
     Timeline
    0.43
     acima
    0.43
     الإنسان
    0.43
    uação
    0.42
     diseñ
    0.41
     alguns
    0.41
     फ़
    0.41
     niin
    0.41
     sheltered
    0.40
    Activations Density 0.000%

    No Known Activations