© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13159
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    cdot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    posedge
    -0.66
    verwijspagina
    -0.64
    <bos>
    -0.58
    тили
    -0.55
    (
    -0.54
     berbentuk
    -0.53
    -0.52
    [
    -0.52
    :
    -0.52
    GEBURTSDATUM
    -0.52
    POSITIVE LOGITS
     itſelf
    1.03
     myſelf
    1.00
    ſelf
    0.95
     himſelf
    0.89
     purpoſe
    0.87
     neceff
    0.82
     themſelves
    0.79
     doInBackground
    0.78
     Wikispecies
    0.77
     ſeveral
    0.77
    Activations Density 4.065%
    No Known Activations