© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10739
    Prev
    Next
    INDEX
    Explanations

    LaTeX document formatting commands.

    oai_token-act-pair · gemini-2.0-flash

    ams

    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
     Stephenson
    -0.50
    úc
    -0.48
     direct
    -0.48
    Link
    -0.47
    вь
    -0.46
     Direct
    -0.46
     vainilla
    -0.45
    extension
    -0.45
    usepackage
    -0.45
    harapkan
    -0.45
    POSITIVE LOGITS
    setVerticalGroup
    1.05
    principalColumn
    0.82
    IndentedString
    0.81
     HasFactory
    0.80
     Wikimedijinoj
    0.79
    IUrlHelper
    0.79
     تضيفلها
    0.74
    RetentionPolicy
    0.74
    ArgsConstructor
    0.74
     endwhile
    0.72
    Activations Density 1.482%

    No Known Activations