© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11213
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are generic and widely used in various forms of speech, reading and media

    oai_token-act-pair · gemini-2.0-flash

    Sharing and providing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.60
     garden
    -0.57
    تقاوى
    -0.56
     tess
    -0.52
    lost
    -0.52
     lost
    -0.52
     Garden
    -0.51
    EndInit
    -0.50
    GraphicsUnit
    -0.49
    WithIOException
    -0.49
    POSITIVE LOGITS
    Personendaten
    0.69
    RegressionTest
    0.66
     ErrIntOverflow
    0.59
    BITDA
    0.56
    ьаж
    0.54
     CreateTagHelper
    0.52
     MainAxisSize
    0.52
    évaluateur
    0.52
     saites
    0.51
     éditoriale
    0.51
    Activations Density 5.443%

    No Known Activations