© 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. 235387
    Prev
    Next
    INDEX
    Explanations

    learned

    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
    nativeElement
    0.46
    igung
    0.43
    know
    0.42
     રીતે
    0.38
    Know
    0.38
     chờ
    0.38
    findById
    0.37
    莴
    0.37
    મો
    0.37
     चौ
    0.36
    POSITIVE LOGITS
     পুর্ব
    0.37
     hukum
    0.37
     мере
    0.35
     Sop
    0.35
     tarda
    0.35
     apres
    0.35
     पूर्णा
    0.35
     Pek
    0.34
     attempts
    0.34
    getPort
    0.34
    Activations Density 0.002%

    No Known Activations