© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38053
    Prev
    Next
    INDEX
    Explanations

    azure resources and services

    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_11_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
    an
    0.54
     rejuvenation
    0.51
    gende
    0.49
    phor
    0.46
     '
    0.44
    action
    0.44
     an
    0.44
     emigration
    0.42
    aciones
    0.42
     delicious
    0.42
    POSITIVE LOGITS
    𝐫
    0.65
    𝐞
    0.60
    𝐳
    0.56
     plufieurs
    0.56
    𝙛
    0.55
    𝐢
    0.52
    𝐁
    0.52
     algorith
    0.51
    𝐟
    0.50
    𝐭
    0.50
    Activations Density 0.042%

    No Known Activations