© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175946
    Prev
    Next
    INDEX
    Explanations

    the

    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
    性を
    0.38
    жности
    0.38
    第二百
    0.37
    ᱕
    0.36
    чү
    0.35
    ่ย
    0.35
     ப
    0.34
    راً
    0.34
     शर्तों
    0.33
    र्ता
    0.33
    POSITIVE LOGITS
     thought
    2.94
    thought
    2.63
    Thought
    2.47
     Thought
    2.44
     pensiero
    1.77
     pensamento
    1.75
     pensée
    1.73
     pensamiento
    1.70
     thoughts
    1.64
     düşün
    1.59
    Activations Density 0.002%

    No Known Activations