© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14037
    Prev
    Next
    INDEX
    Explanations

    words and phrases in Spanish (and to some extent also technical terms "copy", "sites" "description", "product", "figure") and terms related to elections

    oai_token-act-pair · gemini-2.0-flash

    Multiple languages

    np_max-act · gemini-2.0-flash

    proper nouns

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ی
    -0.79
    e
    -0.74
    ümüz
    -0.71
    phology
    -0.68
    lighet
    -0.67
     betweenstory
    -0.67
    ført
    -0.66
    lıyor
    -0.66
    s
    -0.66
    стоинства
    -0.65
    POSITIVE LOGITS
    Parcelize
    0.74
    脚注の使い方
    0.72
     ISNI
    0.68
     Kamer
    0.65
     Pank
    0.63
     Lokales
    0.63
    GraphicsUnit
    0.60
    antMatchers
    0.60
    ,:,
    0.59
    bitter
    0.59
    Activations Density 20.000%

    No Known Activations