© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7958
    Prev
    Next
    INDEX
    Explanations

    training Somali forces

    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
    髪
    0.44
    インテリア
    0.42
     Pun
    0.40
    ellä
    0.39
     المخ
    0.39
    ቲ
    0.38
    ಒ
    0.38
    ၽ
    0.38
    पात
    0.37
    ạt
    0.37
    POSITIVE LOGITS
    伤
    0.39
    amia
    0.37
     Spark
    0.37
    Bigl
    0.37
    ax
    0.36
     Retirement
    0.36
     শর্ত
    0.36
     niez
    0.36
    Spark
    0.35
     darauf
    0.35
    Activations Density 0.004%

    No Known Activations