© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162205
    Prev
    Next
    INDEX
    Explanations

    receiving benefits

    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_2_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
    of
    1.60
    在
    1.33
    信息
    1.31
     in
    1.30
    东西
    1.27
    原因
    1.26
    一個
    1.25
    位置
    1.25
    时间
    1.19
    内容
    1.16
    POSITIVE LOGITS
    ς
    1.23
    4
    1.22
    ים
    1.18
    つの
    1.09
    یی
    1.05
    ‌است
    1.05
    ی
    1.04
    あらゆる
    0.99
    ться
    0.98
    ૪
    0.98
    Activations Density 0.002%

    No Known Activations