© 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. 132154
    Prev
    Next
    INDEX
    Explanations

    Australian places

    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
     銀
    0.45
     nucleon
    0.44
     WOL
    0.43
    nda
    0.42
     Walling
    0.42
     Wolver
    0.41
     ambientale
    0.40
     happening
    0.39
    monkey
    0.39
    㙂
    0.39
    POSITIVE LOGITS
     Macy
    0.39
     macular
    0.39
    霍
    0.39
    ピアス
    0.38
    ফ
    0.38
    IOD
    0.38
    oze
    0.37
    ப்பான்
    0.37
     La
    0.37
    mack
    0.37
    Activations Density 0.000%

    No Known Activations