© 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. 7250
    Prev
    Next
    INDEX
    Explanations

    words and short phrases associated with effort and action

    oai_token-act-pair · gemini-2.0-flash

    do

    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
    ruptedException
    -0.66
     ModelExpression
    -0.58
     Réponses
    -0.57
    AdapterFactory
    -0.57
    Personensuche
    -0.56
     незавершена
    -0.56
     AssemblyCulture
    -0.53
    topbar
    -0.50
    enterOuterAlt
    -0.50
    orianCalendar
    -0.49
    POSITIVE LOGITS
    expandindo
    0.65
    brainly
    0.64
     defaultstate
    0.51
    ).__
    0.49
     initComponents
    0.49
    anthene
    0.49
     congratulations
    0.49
    openConnection
    0.48
    InlineData
    0.48
     tribe
    0.47
    Activations Density 10.068%

    No Known Activations