© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205956
    Prev
    Next
    INDEX
    Explanations

    approximation methods and expansions

    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
     будущем
    0.48
     toekom
    0.44
     буду
    0.43
     хоро
    0.43
     وق
    0.43
     бъде
    0.42
     ца
    0.41
    ϡ
    0.41
     futuro
    0.41
     будущего
    0.41
    POSITIVE LOGITS
    itatively
    0.47
    ouse
    0.46
    (),
    0.45
    rums
    0.45
     pigs
    0.44
     budgets
    0.43
    tà
    0.43
     गईं
    0.43
     leaks
    0.42
    ্তি
    0.42
    Activations Density 0.000%

    No Known Activations