© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4094
    Prev
    Next
    INDEX
    Explanations

    scientific names and classifications, particularly of microorganisms and their taxonomic groups.

    oai_token-act-pair · gemini-2.0-flash

    technical terminology and software-related terms

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

    Biological species and families

    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
     EconPapers
    -0.86
    ImageContext
    -0.80
    InjectAttribute
    -0.67
    Історія
    -0.66
    IndentedString
    -0.65
    下载附件
    -0.65
    oa̍t
    -0.65
    BeginContext
    -0.64
    ,‎
    -0.64
    IsContent
    -0.63
    POSITIVE LOGITS
    viewtopic
    0.49
    xodo
    0.44
    lodash
    0.44
    weeney
    0.43
    tidal
    0.41
    glColor
    0.40
     Super
    0.40
    FormTagHelper
    0.39
    SUPER
    0.39
     kuulu
    0.39
    Activations Density 0.821%

    No Known Activations