Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9675
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with the automotive industry and vehicle diagnostics, particularly related to the OBD-II standard, along with some location names

    oai_token-act-pair · gemini-2.0-flash

    Vehicle service and recalls

    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
    AddTagHelper
    -0.79
    Personensuche
    -0.75
    Diwedd
    -0.74
    setVerticalGroup
    -0.74
    SourceChecksum
    -0.73
     Réponses
    -0.71
    InjectAttribute
    -0.70
     EconPapers
    -0.68
    oa̍t
    -0.67
    AddHtmlAttribute
    -0.65
    POSITIVE LOGITS
    RetentionPolicy
    0.54
     OkHttpClient
    0.53
    ESSMENT
    0.49
     الحره
    0.46
    Pagamento
    0.45
    Caus
    0.45
    wys
    0.45
     PAY
    0.44
    timmt
    0.44
    Tinh
    0.44
    Activations Density 20.402%

    No Known Activations