© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9132
    Prev
    Next
    INDEX
    Explanations

    numbers and decimal points, especially those appearing in data tables or scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    The number 5

    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
    writeFieldEnd
    -0.79
    DockStyle
    -0.74
    setVerticalGroup
    -0.63
    awtextra
    -0.60
    ResumeLayout
    -0.60
     ویکی‌پدیا
    -0.58
     يتيمه
    -0.57
    ValueStyle
    -0.57
    دانشنامهٔ
    -0.56
    Personendaten
    -0.52
    POSITIVE LOGITS
    5
    1.50
     five
    1.41
     fifth
    1.13
     cinq
    1.12
     Five
    1.12
     fünf
    1.09
     vijf
    1.09
     cinco
    1.05
    five
    1.05
    五
    1.03
    Activations Density 1.331%

    No Known Activations