© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157877
    Prev
    Next
    INDEX
    Explanations

    know

    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_50_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
     Kore
    0.40
     scol
    0.40
    ونم
    0.39
     MEDICAL
    0.38
    ="";
    0.38
     medically
    0.38
     hexagonal
    0.37
     sprinkled
    0.37
     haemorrh
    0.37
     withered
    0.37
    POSITIVE LOGITS
     `>=
    0.39
     অ্যাসিড
    0.37
    ༣
    0.37
     مشين
    0.37
    neet
    0.37
     costi
    0.37
     lịch
    0.36
    ᐛ
    0.36
    සා
    0.36
    ษย์
    0.36
    Activations Density 0.002%

    No Known Activations