© 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. 204
    Prev
    Next
    INDEX
    Explanations

    language related to the history and ethics of slavery and human trafficking

    oai_token-act-pair · gemini-2.0-flash

    slavery

    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
    bootstrapcdn
    -0.63
    RegressionTest
    -0.56
    alegal
    -0.54
     noDo
    -0.54
    avigation
    -0.52
    basicConfig
    -0.52
    dirond
    -0.49
    MessageOf
    -0.49
     насељу
    -0.48
    setopt
    -0.48
    POSITIVE LOGITS
    GraphicsUnit
    0.63
     chat
    0.61
    期刊论文
    0.59
    chat
    0.49
    ateness
    0.49
    ussi
    0.48
     chats
    0.47
    مراجع
    0.47
     Shops
    0.47
     Chat
    0.46
    Activations Density 7.578%

    No Known Activations