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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2961
    Prev
    Next
    INDEX
    Explanations

    words that have to do with games, stories, or fiction and that have some element of "Japanese" to them (Kyurangers, Utama, etc)

    oai_token-act-pair · gemini-2.0-flash

    Game updates and expansions

    np_max-act-logits · gemini-2.0-flash
    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
     {
    -0.55
    ->_
    -0.46
    posób
    -0.46
    Спољашње
    -0.45
    )?;
    -0.45
    lıyor
    -0.43
    ORING
    -0.43
    (!__
    -0.43
    はコチラ
    -0.43
    遊ぶ
    -0.43
    POSITIVE LOGITS
    ContentAsync
    0.88
    graphique
    0.62
     disambiguazione
    0.56
    netbeans
    0.56
    MergeFrom
    0.55
    nologue
    0.54
    Britannique
    0.52
    NVIC
    0.52
     الحره
    0.51
    Getenv
    0.51
    Activations Density 2.951%

    No Known Activations