© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15085
    Prev
    Next
    INDEX
    Explanations

    mentions of magazines and when they are referenced

    oai_token-act-pair · gemini-2.0-flash

    magazine publications

    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
    Geplaatst
    -0.72
    ReusableCell
    -0.66
    Personensuche
    -0.61
    BagConstraints
    -0.59
    complexContent
    -0.58
    CodeAttribute
    -0.58
    сылкі
    -0.58
     FetchType
    -0.54
     NSCoder
    -0.52
     Primaria
    -0.50
    POSITIVE LOGITS
    acuation
    0.57
     Town
    0.54
     disambiguazione
    0.50
    bidities
    0.48
     zwierzę
    0.48
    idjan
    0.47
    hysema
    0.47
    Portale
    0.47
    readObject
    0.47
    soort
    0.47
    Activations Density 0.685%

    No Known Activations