© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5525
    Prev
    Next
    INDEX
    Explanations

    mentions of news organizations and employees and the reporting of news

    oai_token-act-pair · gemini-2.0-flash

    words related to journalism and reporting

    np_token-act-pair-logits · gpt-4o-mini

    News and journalism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AsUp
    -0.64
    GOTREF
    -0.63
     beginnetje
    -0.60
    Према
    -0.56
     playboy
    -0.54
     configureStore
    -0.54
    UpInside
    -0.54
    OGND
    -0.52
    पया
    -0.52
     Gaya
    -0.50
    POSITIVE LOGITS
    protoimpl
    0.71
    ználat
    0.58
     recevez
    0.57
     deep
    0.52
     réduite
    0.52
    chtenstein
    0.51
    deep
    0.50
     étro
    0.50
    ărat
    0.48
    indeki
    0.48
    Activations Density 0.739%

    No Known Activations