© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5470
    Prev
    Next
    INDEX
    Explanations

    topics and locations related to war crimes, especially rape in Africa.

    oai_token-act-pair · gemini-2.0-flash

    non-English or technical terms

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

    Conflicts in Africa

    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
     considérons
    -0.51
     colesterol
    -0.50
     المعيارى
    -0.48
     Algérie
    -0.45
     Alkaline
    -0.44
     céré
    -0.44
     زاده
    -0.43
    زاده
    -0.43
    jarat
    -0.42
    mesi
    -0.42
    POSITIVE LOGITS
     محفوظة
    0.80
    QMetaType
    0.77
     виправивши
    0.67
    ">//
    0.67
    __':
    0.65
     pinulongan
    0.63
    TagMode
    0.62
    بوابة
    0.62
    verwijspagina
    0.59
    astéro
    0.59
    Activations Density 1.000%

    No Known Activations