© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124624
    Prev
    Next
    INDEX
    Explanations

    start, run, reverse

    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_37_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
    譏
    0.40
    zin
    0.38
    unar
    0.36
    吐槽
    0.35
    Preparing
    0.34
     பண்ப
    0.34
    xFFFF
    0.34
    Succ
    0.34
    志
    0.34
    寸
    0.34
    POSITIVE LOGITS
     Django
    0.40
     mitochondrial
    0.39
     Deal
    0.37
    omata
    0.37
     scalp
    0.35
     Ayurvedic
    0.35
    ів
    0.34
     کافی
    0.34
     Kamp
    0.34
    FACTORY
    0.34
    Activations Density 0.000%

    No Known Activations