© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9238
    Prev
    Next
    INDEX
    Explanations

    mentions of Turkmenistan and related terms, especially in the context of football (soccer)

    oai_token-act-pair · gemini-2.0-flash

    Turkmen-related content

    np_token-act-pair-logits · gpt-4o-mini

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inter
    -0.42
     eu
    -0.41
    defin
    -0.41
    FindBy
    -0.40
    HideFlags
    -0.38
     intervi
    -0.38
    -0.38
    side
    -0.38
     Ahu
    -0.38
     interference
    -0.38
    POSITIVE LOGITS
    الإنجليزية
    0.94
     autorytatywna
    0.88
     InputDecoration
    0.73
    UnsafeEnabled
    0.73
     betweenstory
    0.67
     مرئيه
    0.64
     Efq
    0.63
     CascadeType
    0.59
    InputBorder
    0.59
     odeur
    0.59
    Activations Density 0.066%

    No Known Activations