© 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. 13110
    Prev
    Next
    INDEX
    Explanations

    code snippets and file operations, including interactions with files and specific characters used in coding

    oai_token-act-pair · gemini-2.0-flash

    file operations or handling

    np_token-act-pair-logits · gpt-4o-mini
    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
     glass
    -0.48
    IntoConstraints
    -0.45
     Ques
    -0.43
    Incoming
    -0.43
    ابي
    -0.42
     moving
    -0.42
     immobilized
    -0.42
    Географиясе
    -0.42
    hens
    -0.42
     Hej
    -0.42
    POSITIVE LOGITS
     صوتيه
    0.83
    rungsseite
    0.82
    
    0.76
    IsContent
    0.74
    InjectAttribute
    0.69
    :✨
    0.68
     ComVisible
    0.68
    liothèque
    0.66
    swire
    0.66
    usercontent
    0.66
    Activations Density 0.760%

    No Known Activations