© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7451
    Prev
    Next
    INDEX
    Explanations

    words realted to car racing

    oai_token-act-pair · gemini-2.0-flash

    race car driving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ConverterFactory
    -0.53
     penerima
    -0.48
     CURLOPT
    -0.47
    qtype
    -0.46
    BufferedReader
    -0.46
     getItemCount
    -0.44
    enschappelijke
    -0.44
     Deep
    -0.44
    CURLOPT
    -0.44
    ScreenState
    -0.43
    POSITIVE LOGITS
     faſt
    0.59
     Indi
    0.59
    SharedDtor
    0.59
    StoryboardSegue
    0.59
    AsUp
    0.58
     Ioan
    0.57
    HtmlAttribute
    0.56
    principalTable
    0.56
    IUrlHelper
    0.56
     houſe
    0.54
    Activations Density 0.700%

    No Known Activations