© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205814
    Prev
    Next
    INDEX
    Explanations

    historical European figures

    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
     envol
    0.43
     lentes
    0.43
     P
    0.41
     pon
    0.40
     par
    0.39
    par
    0.39
     pisc
    0.39
     ren
    0.39
     Pon
    0.39
     acer
    0.38
    POSITIVE LOGITS
    ienna
    0.44
     بیٹ
    0.44
    ▋
    0.44
     undeni
    0.43
     মসজি
    0.41
    LoggedIn
    0.40
     সক্রিয়
    0.38
     bred
    0.38
    肪
    0.38
    sled
    0.38
    Activations Density 0.001%

    No Known Activations