© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13526
    Prev
    Next
    INDEX
    Explanations

    words related to exciting or adventurous stories

    oai_token-act-pair · gemini-2.0-flash

    adventure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    adalajara
    -0.47
     control
    -0.46
    פר
    -0.45
    发表于
    -0.45
    gewiesen
    -0.44
     bỏ
    -0.42
     use
    -0.42
    irus
    -0.42
     analyse
    -0.42
    Builder
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    1.23
    OGND
    0.94
    
    0.88
    adventure
    0.88
    Portale
    0.83
    ViewImports
    0.82
     surla
    0.80
     مشين
    0.79
     AssemblyVersion
    0.79
     adventures
    0.79
    Activations Density 1.305%

    No Known Activations