© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6410
    Prev
    Next
    INDEX
    Explanations

    the word "camp" and related words, such as "mostly active"

    oai_token-act-pair · gemini-2.0-flash

    camp

    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
    o
    -0.64
    s
    -0.63
    t
    -0.59
    te
    -0.49
    d
    -0.49
    formik
    -0.47
    ers
    -0.47
     ―――
    -0.46
     sintético
    -0.46
     chilena
    -0.46
    POSITIVE LOGITS
    yntaxException
    1.13
    WithIOException
    1.03
    aarrggbb
    1.03
    QMetaType
    0.90
    adaptiveStyles
    0.90
     pinulongan
    0.89
    SharedCtor
    0.88
    Neighbour
    0.88
    colourful
    0.87
    criminate
    0.84
    Activations Density 1.016%

    No Known Activations