© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82056
    Prev
    Next
    INDEX
    Explanations

    discuss employee wages and capacity

    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_29_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
     include
    0.32
     daftar
    0.31
    ,
    0.30
    ्यादा
    0.29
     exclude
    0.28
     cliente
    0.28
     DCC
    0.28
     لاءِ
    0.28
    ،
    0.28
     alright
    0.27
    POSITIVE LOGITS
     thisobject
    0.31
     ব্যাপারটা
    0.31
     বিষয়টা
    0.30
     टॉपिक
    0.28
     सेलेना
    0.28
    лянчук
    0.28
    .”.
    0.28
     इन्हे
    0.27
    !”.
    0.27
    journals
    0.27
    Activations Density 0.000%

    No Known Activations