© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10182
    Prev
    Next
    INDEX
    Explanations

    code snippets that end with closing curly brackets or square brackets followed by a semicolon

    oai_token-act-pair · gemini-2.0-flash

    parentheses/semicolons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     for
    -0.61
    .
    -0.57
     K
    -0.51
     to
    -0.50
    "
    -0.50
     de
    -0.49
     an
    -0.49
     за
    -0.48
    -
    -0.47
    鑑
    -0.47
    POSITIVE LOGITS
     Theſe
    0.95
     itſelf
    0.90
     myſelf
    0.89
     Majefty
    0.85
     himſelf
    0.84
     gainera
    0.77
     themſelves
    0.76
     wikipagina
    0.76
     Beſ
    0.76
    UnusedPrivate
    0.75
    Activations Density 0.754%

    No Known Activations