© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    formal patent-like language indicating a need

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or specific domain terms

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

    technical documents

    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
    didSet
    -0.55
     snippetHide
    -0.50
    key
    -0.48
    Vere
    -0.47
     οὐ
    -0.47
    kurat
    -0.46
     gruppe
    -0.46
     Double
    -0.45
    Alte
    -0.45
     @"";
    -0.45
    POSITIVE LOGITS
     AssemblyProduct
    0.66
    ніципалі
    0.64
     CreateTagHelper
    0.64
    Tembelea
    0.63
    
    0.56
    Parcelize
    0.56
    orithmic
    0.55
    restler
    0.54
     oprot
    0.54
    StoreMessageInfo
    0.54
    Activations Density 0.328%

    No Known Activations