© 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. 205039
    Prev
    Next
    INDEX
    Explanations

    1

    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
    Definitely
    0.42
    Certainly
    0.42
     ा
    0.41
     े
    0.41
     certainly
    0.37
     definitely
    0.37
    訟
    0.37
     Definitely
    0.36
     kesin
    0.36
     decisively
    0.36
    POSITIVE LOGITS
    টিয়ে
    0.41
     sunscreen
    0.41
    اهده
    0.39
    อ่ะ
    0.38
     sun
    0.36
     brush
    0.36
     Уда
    0.36
    ěn
    0.35
     美
    0.35
    ಿತ
    0.35
    Activations Density 0.001%

    No Known Activations