© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30618
    Prev
    Next
    INDEX
    Explanations

    computational requirements

    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_31_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
     tanto
    0.36
    学習
    0.36
     обучения
    0.35
    ण्डे
    0.34
     Nursing
    0.34
    梆
    0.34
     LEAR
    0.34
    흉
    0.34
     নাও
    0.34
    ানিতে
    0.34
    POSITIVE LOGITS
     need
    0.66
     requirements
    0.66
     benötigt
    0.62
     potrzeb
    0.60
    Requires
    0.59
     besoin
    0.59
    が必要です
    0.59
     REQUIREMENTS
    0.58
     requirement
    0.57
     dibutuhkan
    0.57
    Activations Density 0.163%

    No Known Activations