© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40274
    Prev
    Next
    INDEX
    Explanations

    tagging resources

    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
    ):
    0.59
     sinter
    0.59
     पहली
    0.58
    ifères
    0.55
     الع
    0.55
     первое
    0.55
     and
    0.54
     પહે
    0.53
     set
    0.53
    ){
    0.52
    POSITIVE LOGITS
    梦想
    0.58
    僵
    0.56
    拟
    0.54
    碰
    0.54
    尟
    0.54
     വിൽപ്പന
    0.52
    ارت
    0.50
    urek
    0.50
    파
    0.50
    几
    0.50
    Activations Density 0.015%

    No Known Activations