© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16426
    Prev
    Next
    INDEX
    Explanations

    Buckingham Palace, historical sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     disciplined
    0.39
    Dew
    0.39
    פט
    0.37
    )\\
    0.36
     පෙ
    0.36
    Tort
    0.36
    Polit
    0.35
    🟦
    0.35
     Fractional
    0.35
    쥬
    0.35
    POSITIVE LOGITS
     мо
    0.41
     टाक
    0.40
     troopers
    0.39
    現實
    0.38
     Ceram
    0.38
    न्द्रीय
    0.38
    高铁
    0.37
     trooper
    0.37
     VIC
    0.36
    ²+
    0.36
    Activations Density 0.017%

    No Known Activations