© 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-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4885
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly C# using statements and related elements like namespaces and class names

    oai_token-act-pair · gemini-2.0-flash

    programming terms and framework keywords

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

    C# code snippets

    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
    Gemeinsame
    -0.55
    featureID
    -0.54
    R
    -0.50
    ",&
    -0.49
     kaarangay
    -0.49
     indexPath
    -0.48
    AfterClass
    -0.48
     foreign
    -0.47
    skon
    -0.45
    S
    -0.45
    POSITIVE LOGITS
     ModelExpression
    0.62
    帖最后由
    0.57
    évaluateur
    0.54
    jsxFileName
    0.53
    AnimationsModule
    0.51
    ORGE
    0.51
    PRNewswire
    0.50
     alberi
    0.50
    Referencie
    0.49
    \{\\
    0.49
    Activations Density 0.434%

    No Known Activations