© 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. 12998
    Prev
    Next
    INDEX
    Explanations

    words related to academic papers like sections, theorems, studies, results, and authors.

    oai_token-act-pair · gemini-2.0-flash

    paper

    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
     CreateTagHelper
    -0.93
    NUMX
    -0.84
     uska
    -0.84
    AddTagHelper
    -0.83
    MemoryWarning
    -0.83
     myſelf
    -0.79
     resourceCulture
    -0.79
     Exacts
    -0.77
     ―――――
    -0.76
    ISupport
    -0.74
    POSITIVE LOGITS
    <bos>
    0.84
    '
    0.59
    (
    0.56
     
    0.54
     I
    0.54
    <
    0.52
    ↵↵
    0.52
    \
    0.52
    ↵
    0.50
    [
    0.49
    Activations Density 3.615%

    No Known Activations