© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166860
    Prev
    Next
    INDEX
    Explanations

    supply

    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_56_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
    पं
    0.39
    Appro
    0.39
    법
    0.38
    మె
    0.36
    Formatted
    0.35
    isValid
    0.35
    法
    0.35
    法的
    0.34
     rady
    0.34
    煞
    0.34
    POSITIVE LOGITS
     supply
    2.38
     Supply
    2.22
    Supply
    2.20
    supply
    2.16
     SUPPLY
    2.03
     공급
    1.92
     सप्लाई
    1.89
     आपूर्ति
    1.86
    供給
    1.84
     supplied
    1.80
    Activations Density 0.001%

    No Known Activations