© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12590
    Prev
    Next
    INDEX
    Explanations

    words related to technology and electronics, particularly in the context of features, expenses, social aspects, options, and safety

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     methods
    -0.95
     policies
    -0.90
     procedures
    -0.90
     tools
    -0.88
     techniques
    -0.88
    methods
    -0.87
     technologies
    -0.85
     options
    -0.84
     activities
    -0.84
     Methods
    -0.84
    POSITIVE LOGITS
     Мексичка
    0.89
    Tikang
    0.71
    
    0.66
    IntoConstraints
    0.64
     AssemblyCulture
    0.63
    $_['
    0.61
     snippetHide
    0.61
     Waray
    0.59
    曖昧さ回避
    0.59
    tvguidetime
    0.57
    Activations Density 12.657%

    No Known Activations