© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12398
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research, technology, and medicine, particularly those focused on innovation, advancement, and improvement in health and environment-related fields.

    oai_token-act-pair · gemini-2.0-flash

    Green/environmental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     yrity
    -0.47
    大部分
    -0.45
     doInBackground
    -0.45
     Michal
    -0.44
     envol
    -0.43
     outside
    -0.42
     olev
    -0.42
     besides
    -0.42
     Résultat
    -0.41
     pick
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    0.84
    WebElementEntity
    0.82
     &___
    0.82
     resourceCulture
    0.81
    WriteBarrier
    0.75
    tagHelperRunner
    0.75
    esModule
    0.75
    (!__
    0.74
    Personensuche
    0.73
     jScrollPane
    0.73
    Activations Density 1.751%

    No Known Activations