© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15328
    Prev
    Next
    INDEX
    Explanations

    descriptions of characteristics of people in a study

    oai_token-act-pair · gemini-2.0-flash

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     onOptions
    -0.54
    ///</
    -0.52
    orElseThrow
    -0.51
     informée
    -0.49
     архивлан
    -0.47
     consultato
    -0.46
    ulous
    -0.46
    testify
    -0.46
     JpaRepository
    -0.46
    labelledby
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.83
    DockStyle
    0.71
     auroit
    0.63
     eût
    0.63
    ξα
    0.61
     الحره
    0.61
     modellen
    0.59
     насељу
    0.59
     étoit
    0.58
    Predecesor
    0.58
    Activations Density 12.308%

    No Known Activations