© 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. 8865
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those representing dates, addresses, and legal codes

    oai_token-act-pair · gemini-2.0-flash

    Non-English/Symbols

    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
     
    -2.23
     $
    -1.26
    $
    -0.65
     
    -0.56
     $\$
    -0.46
     ۴
    -0.44
     £
    -0.44
     $.
    -0.43
     !$
    -0.43
     twenty
    -0.43
    POSITIVE LOGITS
     '\\;'
    1.23
     MainAxisSize
    1.00
    rungsseite
    1.00
     ویکی‌پدی
    0.99
     resourceCulture
    0.90
    存于互联网档案馆
    0.88
    AddTagHelper
    0.88
    ValueStyle
    0.88
    #+#
    0.87
     متعلقه
    0.85
    Activations Density 21.268%

    No Known Activations