© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223976
    Prev
    Next
    INDEX
    Explanations

    scientific method and observation

    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_10_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
     कुठे
    0.41
     כ
    0.41
     mesmerizing
    0.40
    скольку
    0.38
    ও
    0.38
     зміню
    0.38
    迦
    0.38
    皞
    0.36
    も
    0.35
     Еще
    0.35
    POSITIVE LOGITS
    0
    0.55
    3
    0.54
    r
    0.52
    ik
    0.47
    4
    0.43
    pp
    0.41
    5
    0.41
    9
    0.41
    rt
    0.40
    rl
    0.40
    Activations Density 0.058%

    No Known Activations