© 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. 9035
    Prev
    Next
    INDEX
    Explanations

    references to figures, sections, legal code, notes, and steps

    oai_token-act-pair · gemini-2.0-flash

    section

    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
     démocr
    -0.94
     Italijani
    -0.92
     NSCoder
    -0.87
     religieuses
    -0.87
     définiti
    -0.85
     vectorielles
    -0.84
     quelcon
    -0.82
     réfugiés
    -0.82
     financières
    -0.82
     industriels
    -0.81
    POSITIVE LOGITS
     six
    0.57
     four
    0.55
    s
    0.51
     eight
    0.51
     five
    0.50
     
    0.50
     seven
    0.48
     
    0.48
     SZ
    0.48
     three
    0.47
    Activations Density 17.237%

    No Known Activations