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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8659
    Prev
    Next
    INDEX
    Explanations

    angle brackets used for generics and chevrons for less than/greater than, sometimes adjacent to numbers

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    URLException
    -0.57
     littéraire
    -0.51
    antren
    -0.48
    umpulkan
    -0.48
    itag
    -0.48
    만
    -0.47
    idered
    -0.45
    AnchorTagHelper
    -0.45
    pherical
    -0.44
     beams
    -0.44
    POSITIVE LOGITS
    <bos>
    1.00
    StoryboardSegue
    0.84
    awtextra
    0.71
     resourceCulture
    0.68
    /*
    0.68
    +#+#
    0.67
     defaultstate
    0.66
    
    0.65
     CanadaChoose
    0.64
    tagext
    0.63
    Activations Density 1.017%

    No Known Activations