© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233716
    Prev
    Next
    INDEX
    Explanations

    record

    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_46_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
    の話
    0.44
    징
    0.42
    屶
    0.41
     Matching
    0.41
    맞
    0.41
     qīng
    0.40
     разде
    0.40
     맞
    0.39
    paring
    0.39
     మాట్లాడు
    0.39
    POSITIVE LOGITS
     recognize
    0.46
    recogn
    0.45
    Recogn
    0.40
    TRA
    0.40
     recognizing
    0.40
     reconnu
    0.40
    improved
    0.39
    traumatic
    0.39
     unser
    0.38
     recognized
    0.38
    Activations Density 0.002%

    No Known Activations