© 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. 3740
    Prev
    Next
    INDEX
    Explanations

    the word "to" often preceded by verbs like "need"

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    Negative Logits
    <bos>
    -2.56
    afficheront
    -0.65
    цездатний
    -0.62
    oredCriteria
    -0.59
     itſelf
    -0.56
     dedans
    -0.55
     Administrativna
    -0.55
     raiſ
    -0.54
    клопе
    -0.54
     Monfieur
    -0.52
    POSITIVE LOGITS
    __(/*!
    0.64
    makeConstraints
    0.59
     InputDecoration
    0.57
     aca
    0.55
    InputBorder
    0.55
    WithMany
    0.54
     IndexPath
    0.54
    indd
    0.52
    AxisAlignment
    0.52
    üren
    0.50
    Activations Density 0.344%

    No Known Activations