© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195946
    Prev
    Next
    INDEX
    Explanations

    past compared to present

    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_26_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
     पर्सनल
    0.31
    配
    0.30
    ଜ
    0.29
     все
    0.29
     प्लस
    0.28
    ဒီ
    0.28
     किशोर
    0.28
     +,
    0.27
    योग
    0.27
    Lago
    0.27
    POSITIVE LOGITS
     histories
    0.32
     history
    0.31
    chromiumfx
    0.31
    राइट
    0.30
     गांवों
    0.30
    Concluding
    0.30
     sculptural
    0.30
    TimeDict
    0.30
    nBitCount
    0.29
    ოლოდ
    0.29
    Activations Density 0.004%

    No Known Activations