© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205327
    Prev
    Next
    INDEX
    Explanations

    websites and URLs

    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
    规范
    0.38
    propan
    0.38
     lazy
    0.38
    辑
    0.38
     Eucalyptus
    0.36
    狼
    0.36
    艰难
    0.35
     শিব
    0.35
    加载
    0.35
    മായിരുന്നു
    0.34
    POSITIVE LOGITS
     pest
    0.39
     Pest
    0.39
     मेट्रो
    0.39
     மெட்ரோ
    0.38
     debts
    0.37
    ทะ
    0.37
     Scarlett
    0.37
    xym
    0.36
     Fq
    0.36
    ])[
    0.36
    Activations Density 0.000%

    No Known Activations