© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117166
    Prev
    Next
    INDEX
    Explanations

    for-loop iterating over lists

    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_27_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
    餅
    0.41
    リア
    0.40
    饼
    0.40
    生存
    0.39
    影响
    0.39
     സംഭ
    0.38
    क्रम
    0.37
    意义
    0.37
    现实
    0.37
    的影响
    0.37
    POSITIVE LOGITS
     conditioners
    0.45
     conditioner
    0.42
     동시에
    0.37
     сопровожда
    0.37
    䟧
    0.37
     Drei
    0.36
     Baume
    0.36
    cticamente
    0.35
     соответствующих
    0.35
     vitamine
    0.34
    Activations Density 0.007%

    No Known Activations