© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 164879
    Prev
    Next
    INDEX
    Explanations

    hostile, salt water, four

    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_13_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
     부
    0.42
     중요
    0.41
     মোত
    0.41
    al
    0.40
    Japanese
    0.40
     Само
    0.40
    ות
    0.39
    zelf
    0.39
    anic
    0.39
     체
    0.38
    POSITIVE LOGITS
    َى
    0.43
    نا
    0.40
    场
    0.38
     niekoľ
    0.37
    
    0.36
    ٠
    0.36
    年モデル
    0.36
    igator
    0.35
    ším
    0.35
    QUEUE
    0.35
    Activations Density 0.000%

    No Known Activations