© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10591
    Prev
    Next
    INDEX
    Explanations

    words related to outdoor settings and recreational activities

    oai_token-act-pair · gemini-2.0-flash

    Outdoor activities and internet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    in
    -0.60
     best
    -0.59
    s
    -0.54
    ,
    -0.52
     
    -0.52
    K
    -0.50
    k
    -0.50
     outdoor
    -0.49
    of
    -0.47
    f
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    1.28
    parsedMessage
    1.11
    RenderAtEndOf
    1.09
    GEBURTSDATUM
    1.02
    LookAnd
    1.02
    EndInit
    0.96
    RepeatedField
    0.93
    Билгалдахарш
    0.92
    
    0.89
    "){
    0.88
    Activations Density 2.181%

    No Known Activations