© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4844
    Prev
    Next
    INDEX
    Explanations

    words with "res" or "pres" in them

    oai_token-act-pair · gemini-2.0-flash

    references or citations

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

    code, foreign languages, finance

    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
    はじめに
    -0.63
    EndInit
    -0.50
     بيها
    -0.47
     utafitiHapana
    -0.43
    elong
    -0.43
    MethodImpl
    -0.43
     substr
    -0.43
    awtextra
    -0.42
     DbSet
    -0.42
    ++;
    -0.41
    POSITIVE LOGITS
    principalTable
    0.68
    bewerken
    0.66
     referenties
    0.65
    PreferredItem
    0.63
    GeneratedValue
    0.61
     Extragalactic
    0.59
    aarrggbb
    0.56
    govine
    0.56
     مواليد
    0.56
    ByDefault
    0.56
    Activations Density 1.369%

    No Known Activations