© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16012
    Prev
    Next
    INDEX
    Explanations

    various keywords in technical documents and web pages

    oai_token-act-pair · gemini-2.0-flash

    each and every

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    doria
    -0.60
    bbene
    -0.59
     Esau
    -0.54
     Nunca
    -0.51
    ThemeOverlay
    -0.50
    URLException
    -0.48
     dreamstime
    -0.47
     feroit
    -0.47
     PDG
    -0.47
    soever
    -0.47
    POSITIVE LOGITS
     each
    2.20
    each
    1.85
     every
    1.79
     Each
    1.70
    Each
    1.68
     EACH
    1.63
    EACH
    1.59
     chaque
    1.58
    every
    1.42
     каждый
    1.41
    Activations Density 4.732%

    No Known Activations