© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1800
    Prev
    Next
    INDEX
    Explanations

    words indicating where devices can be stored or taken

    oai_token-act-pair · gemini-2.0-flash

    terms related to compact devices or portability

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IsMutable
    -0.87
     Jefus
    -0.82
     Theſe
    -0.82
     CreateTagHelper
    -0.78
     itſelf
    -0.75
     faſt
    -0.75
    Дереккөздер
    -0.72
    脚注の使い方
    -0.72
     ſte
    -0.71
     houſe
    -0.71
    POSITIVE LOGITS
     MongoClient
    0.54
    Na
    0.51
     Na
    0.51
     na
    0.46
    Money
    0.45
     M
    0.43
     I
    0.43
    WindowConstants
    0.42
     ID
    0.41
     Money
    0.41
    Activations Density 1.437%

    No Known Activations