© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8918
    Prev
    Next
    INDEX
    Explanations

    information in titles and headings

    oai_token-act-pair · gemini-2.0-flash

    Web page content/snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Хьажоргаш
    -0.66
     StringTokenizer
    -0.66
    RegistryLite
    -0.64
    RegressionTest
    -0.64
    WireFormat
    -0.63
    detectChanges
    -0.62
    RuleContext
    -0.61
    TypedDataSet
    -0.61
    sizeCache
    -0.61
    Vidite
    -0.61
    POSITIVE LOGITS
    IntoConstraints
    0.69
     Signalez
    0.63
     houſe
    0.63
     greateſt
    0.60
    Παραπομπές
    0.59
     Chriftian
    0.56
     continuación
    0.52
     perfons
    0.52
     }}"></
    0.51
     ſmall
    0.51
    Activations Density 0.654%

    No Known Activations