© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7920
    Prev
    Next
    INDEX
    Explanations

    the word "format"

    oai_token-act-pair · gemini-2.0-flash

    format

    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
    Negative Logits
     Because
    -0.89
    Because
    -0.74
    Erreferentziak
    -0.56
     As
    -0.52
    urgis
    -0.51
    ništ
    -0.50
     organic
    -0.49
    ´)
    -0.49
     Accordingly
    -0.49
    ariste
    -0.49
    POSITIVE LOGITS
    <bos>
    1.24
     CreateTagHelper
    0.62
    WriteTagHelper
    0.53
    hidup
    0.52
    GIH
    0.50
    rrggbb
    0.50
    __":
    0.50
     contigo
    0.49
     mourut
    0.49
    guém
    0.49
    Activations Density 0.800%

    No Known Activations