© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15220
    Prev
    Next
    INDEX
    Explanations

    continents

    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
     gt
    0.41
    জ্ঞ
    0.37
    iod
    0.36
    îte
    0.35
     russe
    0.35
     jordan
    0.35
     deceduto
    0.35
    譞
    0.35
     ٹیک
    0.35
     Brew
    0.34
    POSITIVE LOGITS
     Asia
    1.38
    Asia
    1.28
    Europe
    1.16
     एशिया
    1.14
     asia
    1.13
     Europe
    1.13
    亚洲
    1.12
    亞洲
    1.05
    アジア
    1.05
    asia
    0.96
    Activations Density 0.005%

    No Known Activations