© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6197
    Prev
    Next
    INDEX
    Explanations

    recursion and recursive 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_40_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
    াবাদের
    0.37
    贋
    0.37
    ared
    0.36
    রিদ
    0.35
    ीण
    0.35
     ena
    0.35
     toolPath
    0.35
    㻐
    0.35
    羿
    0.35
    Ṭ
    0.35
    POSITIVE LOGITS
     recursive
    2.78
     recursively
    2.58
    recursive
    2.56
     recursion
    2.55
     Recursive
    2.55
     Recurs
    2.55
    Recursive
    2.52
    递归
    2.50
    Recurs
    2.50
     recurs
    2.38
    Activations Density 0.364%

    No Known Activations