© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3916
    Prev
    Next
    INDEX
    Explanations

    the word "modules"

    oai_token-act-pair · gemini-2.0-flash

    modules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     resourceCulture
    -0.71
     Intelligen
    -0.62
    :✨
    -0.62
     Preferencias
    -0.60
     Cruel
    -0.60
    -------
    -0.60
     Tans
    -0.59
     setPrice
    -0.59
     Assertion
    -0.59
     setName
    -0.59
    POSITIVE LOGITS
    <bos>
    3.02
    '
    0.91
    ’
    0.73
     the
    0.71
    The
    0.71
    ↵
    0.64
    <h2>
    0.63
    Autoritní
    0.59
    let
    0.59
    We
    0.57
    Activations Density 0.173%

    No Known Activations