© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207550
    Prev
    Next
    INDEX
    Explanations

    concerns about

    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_20_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
    釗
    0.20
    单个
    0.20
     ১২শ
    0.20
    वाहक
    0.20
    ynb
    0.20
    LAC
    0.19
     operar
    0.19
    غير
    0.19
    нг
    0.19
    かは
    0.19
    POSITIVE LOGITS
     glum
    0.27
     girls
    0.25
    ertown
    0.25
     আয়োজন
    0.25
     ṣ
    0.25
    ড়ের
    0.24
    女の子
    0.24
     సందర్భంగా
    0.24
     फिस
    0.24
     ಸ
    0.24
    Activations Density 0.003%

    No Known Activations