© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8845
    Prev
    Next
    INDEX
    Explanations

    text segments about informing people or ensuring something

    oai_token-act-pair · gemini-2.0-flash

    informed, educated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     contextLoads
    -0.61
    featureID
    -0.54
    NameInMap
    -0.48
    ξύ
    -0.47
     cuesta
    -0.46
     jamás
    -0.45
     encanto
    -0.45
    Solución
    -0.45
    hurst
    -0.44
     PIX
    -0.44
    POSITIVE LOGITS
     informed
    1.27
     Informed
    1.05
    informed
    1.01
    Informed
    1.01
     intelligent
    0.84
     smart
    0.84
     smarter
    0.82
     educated
    0.81
     INFORM
    0.81
     informs
    0.75
    Activations Density 0.864%

    No Known Activations