© 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. 14727
    Prev
    Next
    INDEX
    Explanations

    the start of code blocks, often preceded by whitespace or containing variable declarations

    oai_token-act-pair · gemini-2.0-flash

    Unusual characters

    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
      
    -1.78
     itſelf
    -0.76
     myſelf
    -0.74
     Efq
    -0.74
     cauſe
    -0.71
     pleaſure
    -0.69
     himſelf
    -0.69
     Monfieur
    -0.68
     themſelves
    -0.68
     purpoſe
    -0.68
    POSITIVE LOGITS
     
    1.04
    &#
    0.76
     „
    0.73
     &#
    0.71
    â
    0.69
     ↑
    0.69
     ""
    0.66
     â
    0.66
    ंदीखरीदारी
    0.66
     •
    0.65
    Activations Density 2.169%

    No Known Activations