© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69171
    Prev
    Next
    INDEX
    Explanations

    legal acts and regulations

    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
     адре
    0.45
     Flügel
    0.43
     lame
    0.43
    弗
    0.43
     Iter
    0.43
     Verbindung
    0.42
     Blynk
    0.41
    iteration
    0.39
     Comanche
    0.39
    स्त
    0.39
    POSITIVE LOGITS
     شه
    0.40
    Sara
    0.37
    QMainWindow
    0.37
    seit
    0.35
     ट्रांसपोर्ट
    0.35
    Ω
    0.35
    тт
    0.35
    hase
    0.34
    getSaveLocation
    0.34
    ﾛ
    0.34
    Activations Density 0.004%

    No Known Activations