© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3420
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and abbreviations associated with rules, regulations, and formal processes especially within institutional settings like correctional facilities or aviation

    oai_token-act-pair · gemini-2.0-flash

    legal/bureaucratic documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     itſelf
    -1.09
     myſelf
    -0.98
     pleaſure
    -0.95
     Jefus
    -0.95
     houſe
    -0.95
     reaſon
    -0.94
     purpoſe
    -0.94
     Majefty
    -0.92
     leaſt
    -0.90
     Efq
    -0.90
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.48
    .
    0.48
    ida
    0.47
    zuf
    0.46
     while
    0.46
     relative
    0.46
     pulled
    0.46
     at
    0.46
     per
    0.44
     for
    0.44
    Activations Density 9.367%

    No Known Activations