© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8523
    Prev
    Next
    INDEX
    Explanations

    mentions of entertainment venues and activities, especially those for both kids and adults

    oai_token-act-pair · gemini-2.0-flash

    stage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    föl
    -0.46
     vej
    -0.43
     saldo
    -0.41
     surla
    -0.41
     میخ
    -0.40
    InSection
    -0.40
    спонд
    -0.39
    aarrggbb
    -0.39
    Affiliations
    -0.38
     spre
    -0.38
    POSITIVE LOGITS
     main
    0.73
    main
    0.71
     stage
    0.69
     Stage
    0.67
     nakalista
    0.66
     STAGE
    0.66
     "'");
    0.63
    __).
    0.63
    rigal
    0.63
    stage
    0.62
    Activations Density 0.326%

    No Known Activations