© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9323
    Prev
    Next
    INDEX
    Explanations

    HTML code for non-breaking spaces and list item delimiters

    oai_token-act-pair · gemini-2.0-flash

    html spacing character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     whilst
    -0.64
    Whilst
    -0.63
    </caption>
    -0.62
    SequentialGroup
    -0.62
    ंदीखरीदारी
    -0.61
     AssemblyCulture
    -0.60
    styleType
    -0.58
    Revenir
    -0.57
     and
    -0.56
    buttonShape
    -0.56
    POSITIVE LOGITS
     heme
    0.66
     ști
    0.66
     hemorr
    0.65
     Mesozoic
    0.65
     heredity
    0.63
     realization
    0.63
     Perché
    0.62
     Offisielt
    0.62
    itudinal
    0.60
     stiefel
    0.60
    Activations Density 1.934%

    No Known Activations