© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1777
    Prev
    Next
    INDEX
    Explanations

    the word "spring" and related concepts of new life and beginnings

    oai_token-act-pair · gemini-2.0-flash

    mentions of "spring" or related seasonal terms

    np_token-act-pair-logits · gpt-4o-mini

    spring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    endphp
    -0.71
    setVerticalGroup
    -0.69
    IntoConstraints
    -0.65
     toit
    -0.55
     StatelessWidget
    -0.52
    boutin
    -0.50
     itſelf
    -0.49
     Tenta
    -0.48
     Sangu
    -0.48
     Alembic
    -0.48
    POSITIVE LOGITS
    ngrx
    0.75
     mar
    0.57
    fall
    0.53
     Fall
    0.52
    jsx
    0.51
    spender
    0.51
    ":[{
    0.50
     nakalista
    0.50
    tonode
    0.50
     season
    0.50
    Activations Density 0.607%

    No Known Activations