© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3746
    Prev
    Next
    INDEX
    Explanations

    words associated with talent shows and celebrities

    oai_token-act-pair · gemini-2.0-flash

    words indicating blocking or disallowing

    np_token-act-pair-logits · gpt-4o-mini

    TV shows

    np_max-act-logits · gemini-2.0-flash
    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
    WithIOException
    -0.70
    expandindo
    -0.68
     démocr
    -0.67
     végétale
    -0.66
     ainfi
    -0.66
    ArgsConstructor
    -0.66
    IBarButtonItem
    -0.65
     photolibrary
    -0.65
     ostavi
    -0.64
     debout
    -0.64
    POSITIVE LOGITS
     Block
    0.54
     dis
    0.53
     Wikimedijinoj
    0.53
    lix
    0.53
     main
    0.52
    posals
    0.51
     Bol
    0.50
     Top
    0.49
     block
    0.47
    imageshack
    0.47
    Activations Density 3.908%

    No Known Activations