© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11649
    Prev
    Next
    INDEX
    Explanations

    code and error messages with quotation marks and angle brackets

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ("
    -0.65
     "..\..\
    -0.55
    TextAppearance
    -0.50
    ({"
    -0.50
    (“
    -0.50
    _("
    -0.49
    ত্ত
    -0.48
     _('
    -0.47
    DateField
    -0.47
     economy
    -0.46
    POSITIVE LOGITS
    HasForeignKey
    0.79
     nakalista
    0.78
    AccessorTable
    0.77
     okuyayım
    0.72
    principalColumn
    0.71
    tvguidetime
    0.65
    cshtml
    0.64
    "],
    0.64
    Filmographie
    0.63
    makeConstraints
    0.61
    Activations Density 0.918%

    No Known Activations