© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16179
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "car" or related words in the context of industries, wedding tours, or V8 engines.

    oai_token-act-pair · gemini-2.0-flash

    cars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.82
     of
    -0.74
     N
    -0.73
     (
    -0.71
     I
    -0.69
     L
    -0.68
     Y
    -0.66
     y
    -0.66
     II
    -0.64
     V
    -0.64
    POSITIVE LOGITS
     houſe
    1.24
     pleaſure
    1.23
    ſelf
    1.20
     Houſe
    1.20
     purpoſe
    1.14
     leaſt
    1.13
     juſ
    1.11
     pngtree
    1.11
    ſelves
    1.09
     ſtate
    1.09
    Activations Density 3.821%

    No Known Activations