© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32650
    Prev
    Next
    INDEX
    Explanations

    scenery

    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
    cka
    0.43
    cki
    0.43
    சன்
    0.37
    间的
    0.37
     Sas
    0.36
    ivu
    0.36
    multipart
    0.36
    刊
    0.36
    嗶
    0.35
    epi
    0.34
    POSITIVE LOGITS
     cảnh
    0.91
    景
    0.88
    境
    0.83
    경
    0.63
     경
    0.60
    㳳
    0.59
    景色
    0.57
    景区
    0.55
    堷
    0.52
     scen
    0.50
    Activations Density 0.004%

    No Known Activations