© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131515
    Prev
    Next
    INDEX
    Explanations

    dog names

    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_50_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
    JET
    0.38
    声
    0.38
    ेश्च
    0.38
     صوت
    0.38
    roqu
    0.38
    Sham
    0.37
     к
    0.36
    voice
    0.36
    Shark
    0.36
    Maple
    0.36
    POSITIVE LOGITS
     anges
    0.43
    yfikacji
    0.41
     unclean
    0.41
    ێکی
    0.39
    孩
    0.38
    완
    0.37
    utérus
    0.37
    ahoo
    0.36
    じゃない
    0.36
     glfw
    0.36
    Activations Density 0.003%

    No Known Activations