© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142605
    Prev
    Next
    INDEX
    Explanations

    mágica

    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_0_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
    Տ
    1.32
    した後
    1.27
    一层
    1.27
    一系列
    1.27
    一部分
    1.23
    ع
    1.22
     آیا
    1.20
     друзья
    1.20
    𝘔
    1.20
     рук
    1.18
    POSITIVE LOGITS
     on
    1.97
    ong
    1.80
    ها
    1.76
    land
    1.65
    ing
    1.60
    та
    1.55
    ↵↵
    1.55
    ным
    1.51
    ।
    1.47
    ed
    1.45
    Activations Density 0.000%

    No Known Activations