© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235344
    Prev
    Next
    INDEX
    Explanations

    please provide me with context

    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_32_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
    anterie
    0.38
    Scientists
    0.37
    ∘
    0.36
     люби
    0.36
    ירות
    0.35
    遵守
    0.34
    懶
    0.34
    好
    0.34
    ኃ
    0.34
     ফুট
    0.34
    POSITIVE LOGITS
     ನನಗೆ
    0.43
     Maa
    0.39
    adz
    0.39
     Happened
    0.39
     election
    0.38
     माझ्या
    0.38
     maan
    0.37
    omination
    0.37
     અમારી
    0.37
     ನನ್ನ
    0.37
    Activations Density 0.018%

    No Known Activations