© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3384
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations and institutions

    oai_token-act-pair · gemini-2.0-flash

    words or terms from diverse languages or contexts

    np_token-act-pair-logits · gpt-4o-mini

    academic/news articles

    np_max-act-logits · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.63
    /***/
    -0.63
     IndexPath
    -0.60
     crossorigin
    -0.59
    nestjs
    -0.54
    יצוב
    -0.54
    ագրություններ
    -0.53
    ImageContext
    -0.53
     protoimpl
    -0.53
     encryption
    -0.53
    POSITIVE LOGITS
     Lordships
    0.56
     disponibilités
    0.54
    Clik
    0.51
     mức
    0.51
    欲
    0.48
    lessness
    0.47
    ONYMOUS
    0.46
     lisse
    0.46
     Serikat
    0.45
    بالإنجليزية
    0.45
    Activations Density 0.435%

    No Known Activations