© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13226
    Prev
    Next
    INDEX
    Explanations

    the word "to" and some words commonly following it like the nouns "post" and "images" and the verb "edit"

    oai_token-act-pair · gemini-2.0-flash

    phrases with the token "to"

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

    UI elements and code

    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
    migrationBuilder
    -0.59
     Phari
    -0.45
    énieurs
    -0.45
     mAdapter
    -0.43
    ┘
    -0.41
     Ergän
    -0.40
    IActionResult
    -0.40
    برگ
    -0.40
    Jedis
    -0.40
     suivants
    -0.40
    POSITIVE LOGITS
     surla
    0.75
     autorytatywna
    0.69
    OpenHelper
    0.68
    Bước
    0.68
    期刊论文
    0.65
     onCreateView
    0.63
    Ծանոթ
    0.62
     مشين
    0.61
    NSYLVANIA
    0.61
     >=",
    0.60
    Activations Density 0.208%

    No Known Activations