© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196383
    Prev
    Next
    INDEX
    Explanations

    network

    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
    genden
    0.39
     testing
    0.37
    賓
    0.37
     முடிந்த
    0.37
    _[
    0.36
     guest
    0.36
     testen
    0.36
    🆈
    0.35
     тести
    0.35
    refour
    0.35
    POSITIVE LOGITS
     বিজ্ঞ
    0.45
    创建一个
    0.42
     ciência
    0.42
    त्ते
    0.40
    science
    0.39
    ZA
    0.39
    Science
    0.39
    澳
    0.38
    創建
    0.38
     caza
    0.37
    Activations Density 0.002%

    No Known Activations