© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9997
    Prev
    Next
    INDEX
    Explanations

    text referring to car handling, especially in difficult driving conditions

    oai_token-act-pair · gemini-2.0-flash

    Car descriptions and 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    LookAnd
    -0.55
     El
    -0.47
    principalTable
    -0.46
     caras
    -0.45
     nahilalakip
    -0.43
    bin
    -0.42
     Wells
    -0.41
     Bog
    -0.40
    boda
    -0.40
     Buck
    -0.40
    POSITIVE LOGITS
     disambiguazione
    0.80
    HtmlAttribute
    0.74
    exitRule
    0.72
    AnimationsModule
    0.68
    Geplaatst
    0.67
     ویکی‌پدیای
    0.65
    .³
    0.65
     textStatus
    0.64
     Malabar
    0.63
    ainville
    0.62
    Activations Density 2.790%

    No Known Activations