© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206118
    Prev
    Next
    INDEX
    Explanations

    large language models (LLMs)

    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_25_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
    lilik
    0.38
     موج
    0.36
    年月日
    0.36
    ं
    0.36
    जैसा
    0.35
    rio
    0.35
    之路
    0.34
    cento
    0.34
    ື່ອ
    0.34
    agl
    0.33
    POSITIVE LOGITS
    під
    0.38
     crab
    0.38
    토
    0.37
    וס
    0.37
    individu
    0.37
    귤
    0.37
    ᄐ
    0.36
     difficultés
    0.36
     pêche
    0.35
    𝘁
    0.34
    Activations Density 0.002%

    No Known Activations