© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20228
    Prev
    Next
    INDEX
    Explanations

    del

    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_56_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
      
    0.44
    ุน
    0.36
     Laboratories
    0.35
    واج
    0.35
     乀
    0.34
     SCIENCES
    0.33
    怪
    0.33
    神奇
    0.32
     মোক
    0.31
    ✧
    0.31
    POSITIVE LOGITS
     del
    3.42
    del
    3.20
    Del
    3.16
     Del
    2.94
    DEL
    2.75
     DEL
    2.64
     دل
    2.27
    델
    2.09
    デル
    2.08
     dell
    2.00
    Activations Density 0.010%

    No Known Activations