© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11466
    Prev
    Next
    INDEX
    Explanations

    lines that reference the DOM

    oai_token-act-pair · gemini-2.0-flash

    programming concepts or methods

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    klart
    -0.50
     wacht
    -0.49
    OIR
    -0.40
    samt
    -0.40
     debole
    -0.40
     فريبيس
    -0.40
    inct
    -0.40
     HONORABLE
    -0.39
    laquo
    -0.39
    dcc
    -0.39
    POSITIVE LOGITS
     typelib
    0.79
    RectangleBorder
    0.76
    UnusedPrivate
    0.74
    MethodManager
    0.73
     Référence
    0.69
    ButterKnife
    0.66
    +#+
    0.66
    cshtml
    0.66
    makeConstraints
    0.65
    principalTable
    0.65
    Activations Density 0.201%

    No Known Activations