© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8955
    Prev
    Next
    INDEX
    Explanations

    instances of informal language usage, like fragments, interjections, and emoticons, often within what appears to be a chat session

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act-logits · gemini-2.0-flash

    '

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     un
    -0.45
    ,
    -0.44
    felder
    -0.38
    thong
    -0.38
    ntä
    -0.37
    日子
    -0.36
     avere
    -0.36
    mtable
    -0.35
     und
    -0.34
    ctility
    -0.34
    POSITIVE LOGITS
    empêcher
    0.77
    ientôt
    0.69
    occuper
    0.65
    expliquer
    0.63
    arrêter
    0.63
    脚注の使い方
    0.61
     Jefus
    0.59
     Abonnez
    0.59
     Taktlose
    0.59
    atteindre
    0.59
    Activations Density 1.264%

    No Known Activations