© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2547
    Prev
    Next
    INDEX
    Explanations

    prepositions or words used as prepositions.

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    tioners
    -0.59
    createCanvas
    -0.52
     Canadians
    -0.51
     guys
    -0.51
    alers
    -0.48
     canadi
    -0.48
     dudes
    -0.47
    pagnols
    -0.47
    verns
    -0.47
    cibles
    -0.46
    POSITIVE LOGITS
     the
    0.78
     marquées
    0.73
    UrlResolution
    0.68
     complètes
    0.66
     financières
    0.64
     définiti
    0.64
    InjectAttribute
    0.60
     élevés
    0.59
     betrek
    0.59
    balleur
    0.58
    Activations Density 3.384%

    No Known Activations