© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11672
    Prev
    Next
    INDEX
    Explanations

    mentions of Donald Trump and his family in association with verbs and associated prepositions.

    oai_token-act-pair · gemini-2.0-flash

    governments granting or denying

    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
    NameInMap
    -0.62
     useStyles
    -0.57
    LookAnd
    -0.55
    afficheront
    -0.52
     ExecuteAsync
    -0.49
     jspb
    -0.48
     Guarantee
    -0.48
    contentLoaded
    -0.47
     receives
    -0.47
    ertal
    -0.47
    POSITIVE LOGITS
    badlogic
    0.60
     NSCoder
    0.56
     mijne
    0.55
     affari
    0.52
     azért
    0.51
    êté
    0.51
    Datuak
    0.51
     betrokken
    0.50
    
    0.50
    crollView
    0.49
    Activations Density 7.735%

    No Known Activations