© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 164596
    Prev
    Next
    INDEX
    Explanations

    contact information

    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_31_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
    竭
    0.40
     വില
    0.35
     звер
    0.35
    瀏
    0.35
     ולא
    0.34
    驚
    0.34
     తెలు
    0.34
    ዋል።
    0.33
    儲
    0.33
     ব্যাপ
    0.33
    POSITIVE LOGITS
     Removal
    0.41
     kaldır
    0.39
     exécut
    0.38
     unloaded
    0.37
    મત
    0.37
     diamètre
    0.36
    ళ
    0.36
     Sonata
    0.36
    dött
    0.36
     rimu
    0.36
    Activations Density 0.003%

    No Known Activations