© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217282
    Prev
    Next
    INDEX
    Explanations

    memory allocation and pointers

    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_31_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
     disregarding
    0.36
    וחות
    0.36
     तहे
    0.35
    وفيق
    0.35
    দন্ত
    0.34
     perceives
    0.34
     Fractals
    0.33
    공
    0.33
     ایپلی
    0.33
     Taxes
    0.33
    POSITIVE LOGITS
    XII
    0.41
    aima
    0.39
    XIV
    0.38
     hal
    0.37
    藕
    0.37
    hal
    0.37
     proven
    0.35
     av
    0.35
    XIII
    0.35
     Samaj
    0.35
    Activations Density 0.001%

    No Known Activations