© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16512
    Prev
    Next
    INDEX
    Explanations

    she/her referent + vicuna/organization/value

    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_15_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
     evi
    0.18
     N
    0.17
     Yok
    0.16
    ointe
    0.16
     کرسک
    0.15
     PPG
    0.15
    âtel
    0.15
     вашу
    0.15
     Pap
    0.14
     Kiểm
    0.14
    POSITIVE LOGITS
     prejudices
    0.18
     murderous
    0.16
    റ്റർ
    0.16
    ције
    0.16
     treason
    0.16
     գ
    0.16
     prejudice
    0.15
    ܝܢ
    0.15
     този
    0.15
     preju
    0.15
    Activations Density 0.024%

    No Known Activations