© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4765
    Prev
    Next
    INDEX
    Explanations

    words related to gear shifting in vehicles and some words pertaining to childhood/development and smoking/addiction.

    oai_token-act-pair · gemini-2.0-flash

    car transmissions

    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
     esternos
    -1.23
    setVerticalGroup
    -1.16
    expandindo
    -1.13
     مرئيه
    -1.09
     betweenstory
    -1.09
    TagMode
    -1.09
    MessageTagHelper
    -1.01
    WithIOException
    -1.01
    ScopeManager
    -1.00
    parsedMessage
    -1.00
    POSITIVE LOGITS
     
    0.55
    <bos>
    0.51
    .
    0.44
     der
    0.44
     B
    0.43
     [
    0.42
     "
    0.42
     (
    0.42
     die
    0.40
     top
    0.40
    Activations Density 5.871%

    No Known Activations