© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196812
    Prev
    Next
    INDEX
    Explanations

    world wonders

    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_46_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
     S
    1.09
     الس
    0.73
    S
    0.68
     एस
    0.57
    Ｓ
    0.53
     הס
    0.51
    𝑆
    0.48
     എസ്
    0.46
     எஸ்
    0.46
     এস
    0.46
    POSITIVE LOGITS
    keto
    0.48
    THREE
    0.44
     ireo
    0.41
    捻
    0.41
    Cline
    0.40
     THREE
    0.40
    ংশে
    0.40
     Couture
    0.39
    Three
    0.38
    ﭼ
    0.38
    Activations Density 0.018%

    No Known Activations