© 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
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140672
    Prev
    Next
    INDEX
    Explanations

    p

    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
    സീ
    0.40
    ්‍ය
    0.39
     Contractors
    0.39
    하시
    0.37
     మాట్లాడుతూ
    0.37
     சூர
    0.37
    ዛ
    0.36
    цый
    0.35
    zyma
    0.35
     Quỳnh
    0.35
    POSITIVE LOGITS
     P
    0.44
    եր
    0.42
     PBL
    0.41
     appId
    0.40
     વર્
    0.39
     П
    0.39
    काला
    0.38
     достав
    0.37
    ংলার
    0.37
    LaunchScheme
    0.37
    Activations Density 0.001%

    No Known Activations