© 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. 336
    Prev
    Next
    INDEX
    Explanations

    negative numbers, division symbols, and parentheses, often within the context of mathematical expressions or coded language.

    oai_token-act-pair · gemini-2.0-flash

    parenthesis

    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
    me
    -0.66
    mA
    -0.52
    mes
    -0.50
    mi
    -0.49
    m
    -0.48
    mia
    -0.48
    msi
    -0.47
    men
    -0.47
    mt
    -0.47
    mele
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.64
     متعلقه
    0.60
    VersionUID
    0.59
    ca
    0.55
    WebServlet
    0.54
     مرئيه
    0.54
    WebVitals
    0.54
    tagHelper
    0.52
    edoc
    0.52
    enance
    0.51
    Activations Density 18.790%

    No Known Activations