© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51658
    Prev
    Next
    INDEX
    Explanations

    logging and printing function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
     except
    0.37
     लिखे
    0.37
    웍
    0.36
     disturbs
    0.36
     Aux
    0.35
     assail
    0.35
    ostatic
    0.35
     attackers
    0.34
     rapporter
    0.34
     commenting
    0.33
    POSITIVE LOGITS
    ifert
    0.39
    熟悉的
    0.38
    ima
    0.38
    以
    0.38
    DisplayStyle
    0.37
    パーク
    0.37
     legalized
    0.37
     logística
    0.37
    साद
    0.36
    公园
    0.36
    Activations Density 0.002%

    No Known Activations