© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2228
    Prev
    Next
    INDEX
    Explanations

    code, timestamp and HTTP url patterns.

    oai_token-act-pair · gemini-2.0-flash

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    .
    -0.57
    URLException
    -0.53
    ядок
    -0.46
    گزاری
    -0.43
     graden
    -0.43
    INLINE
    -0.42
     automatiques
    -0.42
    یک
    -0.42
    ViewImports
    -0.42
    ,\
    -0.41
    POSITIVE LOGITS
     Projektu
    0.70
     propOrder
    0.68
    LookAnd
    0.68
    tadır
    0.65
    esterday
    0.64
    pædia
    0.63
    NgModule
    0.62
    ignal
    0.60
    TypedDataSet
    0.59
    edoc
    0.59
    Activations Density 4.694%

    No Known Activations