© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2818
    Prev
    Next
    INDEX
    Explanations

    references to locations, especially geographical locations

    oai_token-act-pair · gemini-2.0-flash

    Ang

    np_max-act-logits · gemini-2.0-flash

    say "capitalized ethnicities" Method used: 2 — tokens after are capitalized ethnicity names

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    writeFieldEnd
    -0.84
    España
    -0.75
    PostInfinity
    -0.73
    Asian
    -0.73
     african
    -0.73
     taiwan
    -0.73
    Spain
    -0.72
    Hindu
    -0.71
    зулта
    -0.71
     Europe
    -0.71
    POSITIVE LOGITS
     ang
    0.70
     Ang
    0.57
    beginTransaction
    0.55
     ANG
    0.52
     ger
    0.52
    Ang
    0.51
    PerformLayout
    0.49
     Ger
    0.49
    ANG
    0.48
    ang
    0.46
    Activations Density 2.066%

    No Known Activations