© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    words and phrases from Southeast Asian languages related to food

    oai_token-act-pair · gemini-2.0-flash

    Malay/Indonesian language

    np_max-act-logits · 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
     ModelExpression
    -0.72
     kasarigan
    -0.55
    ardez
    -0.52
    mappedBy
    -0.51
    LookAnd
    -0.50
     vigueur
    -0.49
    raszamy
    -0.49
    dientemente
    -0.48
    trui
    -0.47
    MeasureSpec
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.67
    InjectAttribute
    0.58
    bandcamp
    0.51
     papillon
    0.51
     AssemblyCompany
    0.50
    出版年
    0.49
    RequestQueue
    0.48
    ])),
    0.48
    Revenir
    0.48
    ))^
    0.47
    Activations Density 0.242%

    No Known Activations