© 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. 4628
    Prev
    Next
    INDEX
    Explanations

    units of measure

    oai_token-act-pair · gemini-2.0-flash

    strings related to measurement units and organizational terms

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

    meters

    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
    contentLoaded
    -0.81
     חיצוניים
    -0.75
    yntaxException
    -0.75
    abetes
    -0.71
    FormTagHelper
    -0.68
    DeleteBehavior
    -0.68
     ExecuteAsync
    -0.67
    NewUrlParser
    -0.65
    出版年
    -0.63
     newOwner
    -0.63
    POSITIVE LOGITS
    новништво
    0.58
    BagConstraints
    0.57
     követ
    0.49
     organisatie
    0.49
     organization
    0.49
     jadx
    0.49
    inut
    0.47
    organizzazione
    0.46
     compatriots
    0.45
    ags
    0.44
    Activations Density 0.941%

    No Known Activations