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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14972
    Prev
    Next
    INDEX
    Explanations

    instances of the words "has", "have", and "had," as well as some miscellaneous words used to describe a team or a player

    oai_token-act-pair · gemini-2.0-flash

    has

    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
    SuspendLayout
    -0.68
    AddTagHelper
    -0.49
    rosy
    -0.48
    ilhas
    -0.48
     doubtnut
    -0.47
     AssemblyVersion
    -0.47
    cream
    -0.47
    PII
    -0.46
     tarn
    -0.45
    Bronnen
    -0.45
    POSITIVE LOGITS
    BASEPATH
    0.49
    zmir
    0.49
    zorg
    0.49
    ndor
    0.47
    yeth
    0.47
    CompleteListener
    0.47
    HandleFunc
    0.47
    ropolitana
    0.47
     useParams
    0.46
    DJANGO
    0.46
    Activations Density 3.019%

    No Known Activations