© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3516
    Prev
    Next
    INDEX
    Explanations

    language related to political events, and specifically to elections and political disputes in Africa

    oai_token-act-pair · gemini-2.0-flash

    news articles

    np_max-act-logits · gemini-2.0-flash
    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
    Personendaten
    -0.68
     BorderSide
    -0.67
    مصادر
    -0.67
     Anfitrión
    -0.63
     plegable
    -0.60
     שוליים
    -0.58
    InitStruct
    -0.58
     Syrie
    -0.57
    CodedInputStream
    -0.57
    URIS
    -0.54
    POSITIVE LOGITS
    +#+#
    0.69
    IUrlHelper
    0.61
    plen
    0.50
     насељу
    0.47
    Ữ
    0.46
    Personensuche
    0.46
    +:+
    0.46
     nở
    0.45
    ┛
    0.45
     pleins
    0.43
    Activations Density 1.117%

    No Known Activations