© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 80174
    Prev
    Next
    INDEX
    Explanations

    human rights organizations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     হু
    0.40
    কোনও
    0.39
     சந்திர
    0.39
     తీసుకోవ
    0.39
    annabin
    0.39
     الحس
    0.38
     anderer
    0.38
     햇
    0.37
     hoodies
    0.37
     عوام
    0.37
    POSITIVE LOGITS
    Mo
    0.42
    Png
    0.37
    ੭
    0.37
    mtext
    0.37
    ளம்
    0.36
     relinquished
    0.36
    mo
    0.36
    قط
    0.36
    για
    0.35
    kata
    0.35
    Activations Density 0.000%

    No Known Activations