© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60014
    Prev
    Next
    INDEX
    Explanations

    Japanese/Korean companies

    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_59_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
     元
    0.43
     معاد
    0.37
    元的
    0.37
     투
    0.37
     시간이
    0.37
    文章
    0.36
     중요한
    0.36
     demain
    0.36
     去
    0.35
     aware
    0.35
    POSITIVE LOGITS
    Ja
    0.55
    、
    0.45
    ja
    0.44
     Ja
    0.43
    は
    0.42
    Produ
    0.41
    that
    0.41
    、「
    0.40
    代表
    0.40
    fifty
    0.40
    Activations Density 0.000%

    No Known Activations