© 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. 7247
    Prev
    Next
    INDEX
    Explanations

    posts from programming forums asking for help debugging code

    oai_token-act-pair · gemini-2.0-flash

    technical keywords and programming concepts

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

    Something failing/not working

    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
     we
    -0.72
    让我们
    -0.69
    我们
    -0.63
    讓我們
    -0.61
     ourselves
    -0.61
    We
    -0.58
    we
    -0.58
     我们
    -0.56
     We
    -0.56
    我们在
    -0.56
    POSITIVE LOGITS
    SourceChecksum
    1.01
     ComVisible
    0.82
     FetchType
    0.80
     سكانية
    0.78
    MemoryWarning
    0.78
    XmlAccessorType
    0.76
     @"/
    0.75
    TintMode
    0.73
     GenerationType
    0.71
     فريبيس
    0.70
    Activations Density 5.868%

    No Known Activations