© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14404
    Prev
    Next
    INDEX
    Explanations

    project setup and structure

    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_34_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
     কাশ্ম
    0.41
    滷
    0.37
    OnUiThread
    0.37
    ائمة
    0.37
     Medicaid
    0.36
    ariu
    0.36
    tariff
    0.35
    ruž
    0.35
    ர்ப்பு
    0.35
    ᱒
    0.35
    POSITIVE LOGITS
     templates
    0.91
     template
    0.91
    テンプレート
    0.86
     Templates
    0.78
     generators
    0.78
    template
    0.77
    Template
    0.76
     generator
    0.76
    模板
    0.76
    templates
    0.75
    Activations Density 0.145%

    No Known Activations