© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7137
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific studies

    oai_token-act-pair · gemini-2.0-flash

    Research paper abstracts

    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
     resourceCulture
    -0.66
    TagHelper
    -0.65
    出版年
    -0.62
    StructEnd
    -0.61
    stateProvider
    -0.61
    Autoritní
    -0.60
    TagMode
    -0.60
    tagHelperRunner
    -0.60
    bootstrapcdn
    -0.59
    }))
    -0.59
    POSITIVE LOGITS
     Cap
    0.47
    ▻
    0.45
     judic
    0.45
     absurdity
    0.45
    pat
    0.45
     honoured
    0.45
     muualla
    0.45
    ZE
    0.44
     vulgaires
    0.44
     OMITBAD
    0.44
    Activations Density 8.033%

    No Known Activations