© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32686
    Prev
    Next
    INDEX
    Explanations

    **

    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_50_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
     നിയമ
    0.34
     ril
    0.34
     Britain
    0.34
    ట
    0.33
     Brian
    0.33
    akah
    0.33
     André
    0.33
    راهيم
    0.32
     nuclé
    0.32
    界
    0.32
    POSITIVE LOGITS
    des
    0.46
    Des
    0.45
    DES
    0.43
    ignons
    0.40
    mages
    0.40
     cfp
    0.40
     জেড
    0.39
     desorption
    0.39
     inj
    0.39
    emons
    0.38
    Activations Density 0.001%

    No Known Activations