© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6639
    Prev
    Next
    INDEX
    Explanations

    locations, nationalities, and royalty

    oai_token-act-pair · gemini-2.0-flash

    nationalities or languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     English
    -0.63
    English
    -0.54
     english
    -0.52
     ENGLISH
    -0.52
    ใจ
    -0.47
    Transcripción
    -0.47
     nash
    -0.44
    Décès
    -0.43
    сно
    -0.43
    grà
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.72
    FormTagHelper
    0.68
     ProtoMessage
    0.62
     StatelessWidget
    0.61
    Autoritní
    0.61
    jspx
    0.58
     StatefulWidget
    0.57
     colspan
    0.57
    ContentAsync
    0.57
     Roskov
    0.56
    Activations Density 2.714%

    No Known Activations