© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    the word "that", sometimes in association with government terms

    oai_token-act-pair · gemini-2.0-flash

    code snippets and excerpts

    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
     is
    -1.95
     are
    -1.34
     be
    -1.05
     είναι
    -0.85
     là
    -0.83
    的是
    -0.73
     am
    -0.70
     está
    -0.68
     zijn
    -0.67
    คือ
    -0.66
    POSITIVE LOGITS
     EconPapers
    0.83
    rrggbb
    0.66
    PreferredItem
    0.65
    adaptiveStyles
    0.57
    setVerticalGroup
    0.56
    BASELINE
    0.54
     CURIAM
    0.54
    
    0.52
     myſelf
    0.52
    pośred
    0.51
    Activations Density 0.914%

    No Known Activations