© 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-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13407
    Prev
    Next
    INDEX
    Explanations

    code examples and explanations, specifically in JavaScript

    oai_token-act-pair · gemini-2.0-flash

    pronouns and demonstratives

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

    code and mixed languages

    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
     незавершена
    -0.81
     propOrder
    -0.68
     通販
    -0.67
    Geplaatst
    -0.61
    sbericht
    -0.58
    enumii
    -0.58
    
    -0.57
    WithEmail
    -0.56
     henvisninger
    -0.55
    €)
    -0.55
    POSITIVE LOGITS
     the
    0.56
     se
    0.55
     this
    0.54
     these
    0.53
     there
    0.52
    Serve
    0.47
     va
    0.46
     any
    0.44
     those
    0.42
     inne
    0.42
    Activations Density 1.334%

    No Known Activations