© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3236
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are capitalized

    oai_token-act-pair · gemini-2.0-flash

    cat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     cat
    -1.13
     Cat
    -1.03
    Cat
    -1.02
    cat
    -0.96
    DoubleQuotes
    -0.94
    CAT
    -0.90
     cats
    -0.88
     GenerationType
    -0.87
     CAT
    -0.87
    cats
    -0.85
    POSITIVE LOGITS
    status
    0.49
    Status
    0.47
     pinulongan
    0.46
     status
    0.45
     stuk
    0.45
     hiszen
    0.44
     Status
    0.44
     producing
    0.43
     tasche
    0.42
    hemiah
    0.42
    Activations Density 11.902%

    No Known Activations