© 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. 11937
    Prev
    Next
    INDEX
    Explanations

    Asian names, especially Chinese names

    oai_token-act-pair · gemini-2.0-flash

    Chinese names

    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
     betweenstory
    -0.65
    tadır
    -0.65
    ьаж
    -0.64
     Walkover
    -0.60
     ivelany
    -0.58
     calendriers
    -0.56
    )?;
    -0.56
    tvguidetime
    -0.56
    hetically
    -0.56
     特写
    -0.56
    POSITIVE LOGITS
     feroit
    0.60
     auroit
    0.59
     enfans
    0.57
     varandra
    0.57
     étoit
    0.56
     étranger
    0.56
     quæ
    0.55
     aveug
    0.54
     larmes
    0.54
     oreilles
    0.54
    Activations Density 3.039%

    No Known Activations