© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174810
    Prev
    Next
    INDEX
    Explanations

    heating and cooling cycles

    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_20_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
    c
    0.58
    Demon
    0.52
    Stream
    0.49
    anny
    0.49
    3
    0.46
    cian
    0.45
    1
    0.44
    Family
    0.43
     ***
    0.43
    Application
    0.43
    POSITIVE LOGITS
    makeConstraints
    0.47
     blockSize
    0.43
     ጡ
    0.43
    imageNamed
    0.42
     моде
    0.42
     polyp
    0.42
     platelet
    0.41
    বুঝ
    0.41
     legen
    0.41
    খে
    0.41
    Activations Density 0.000%

    No Known Activations