© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10727
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to automobiles and driving

    oai_token-act-pair · gemini-2.0-flash

    vehicle operation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Aholisi
    -0.59
    änner
    -0.57
     Driver
    -0.57
     Numerade
    -0.55
     Drivers
    -0.53
     driving
    -0.52
    driver
    -0.52
     Drapeau
    -0.52
    Driver
    -0.51
    ThroughAttribute
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.59
    chengladbach
    0.56
    TemporalType
    0.56
    UseVisualStyle
    0.52
     Ortsteil
    0.51
     LUMP
    0.51
     springfox
    0.50
    IBOutlet
    0.48
    
    0.48
    XmlAccessType
    0.48
    Activations Density 8.924%

    No Known Activations