© 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. 205548
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     Ultra
    2.38
    Ultra
    2.34
     ultra
    2.27
    ultra
    2.11
     ULTRA
    2.02
     अल्ट्रा
    1.77
     ultr
    1.66
     U
    1.64
     ультра
    1.63
     Ultr
    1.36
    POSITIVE LOGITS
    amacare
    0.37
     रामानंद
    0.35
     Kartik
    0.35
    慓
    0.35
    yuk
    0.35
    ❈
    0.34
     பொ
    0.33
    ശന
    0.33
    టకు
    0.33
    Marion
    0.33
    Activations Density 0.030%

    No Known Activations