© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12223
    Prev
    Next
    INDEX
    Explanations

    the names of Japanese things, including people, places, media, and concepts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Japanese
    -1.86
    Japanese
    -1.61
     Japan
    -1.59
     japanese
    -1.45
     JAPAN
    -1.44
     Japon
    -1.42
    Japan
    -1.41
     Jepang
    -1.39
     Jap
    -1.38
     japan
    -1.38
    POSITIVE LOGITS
    IndentedString
    0.63
    //
    0.57
    _))
    0.57
    }}}}
    0.55
    "])
    0.54
     betweenstory
    0.53
    =?";
    0.52
    queryInterface
    0.52
    <bos>
    0.52
    osoba
    0.52
    Activations Density 1.814%

    No Known Activations