© 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. 9151
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those pertaining to measurements and statistics

    oai_token-act-pair · gemini-2.0-flash

    numbers and 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
     Chwiliwch
    -0.54
    RegressionTest
    -0.50
     esternos
    -0.49
     ویکی‌پدی
    -0.47
    GEBURTSDATUM
    -0.45
    SourceChecksum
    -0.44
    ніципа
    -0.43
    artament
    -0.41
    LookAnd
    -0.41
     Савезне
    -0.41
    POSITIVE LOGITS
       
    0.94
     □
    0.94
     ¯
    0.93
     ™
    0.91
     {$\
    0.91
     ®
    0.90
     (°
    0.90
     ›
    0.90
     ☐
    0.90
     ¢
    0.90
    Activations Density 31.792%

    No Known Activations