© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197654
    Prev
    Next
    INDEX
    Explanations

    woman's role

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     برند
    0.42
     Paise
    0.42
    샴
    0.42
     Brandon
    0.41
    Brandon
    0.40
     Ranc
    0.40
     AN
    0.40
     matemático
    0.39
    痪
    0.39
     Bran
    0.39
    POSITIVE LOGITS
    kitchen
    0.43
    ora
    0.43
    Bottom
    0.41
    era
    0.40
    Kitchen
    0.40
     kitchen
    0.39
    uza
    0.39
    Interfaces
    0.39
    лага
    0.38
     Kitchen
    0.38
    Activations Density 0.000%

    No Known Activations