Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7218
    Prev
    Next
    INDEX
    Explanations

    the Japanese phrase "いうと[十返]{じゅうかえ}ってくる"

    oai_token-act-pair · gemini-2.0-flash

    くるってくる

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     $_"
    -1.02
     whoſe
    -0.98
     itſelf
    -0.93
     Efq
    -0.92
     Jefus
    -0.87
     myſelf
    -0.84
    ſhip
    -0.84
     fince
    -0.82
     houſe
    -0.82
     היתה
    -0.81
    POSITIVE LOGITS
    发表于
    0.84
    __*/
    0.82
    bootstrapcdn
    0.79
    原始内容存档于
    0.73
    +:+
    0.73
    usepackage
    0.70
    ArgumentParser
    0.67
    Disappear
    0.67
    ContentAsync
    0.66
    mybatisplus
    0.66
    Activations Density 2.151%

    No Known Activations