© 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. 517
    Prev
    Next
    INDEX
    Explanations

    the conjunction "to" appearing near auxiliary verbs and sometimes location prepositions

    oai_token-act-pair · gemini-2.0-flash

    visit

    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
    -0.57
     consultato
    -0.57
     الحره
    -0.56
     BoxDecoration
    -0.55
     >::
    -0.53
    ArgsConstructor
    -0.50
     GetEnumerator
    -0.50
    
    -0.48
     Exploring
    -0.48
    XmlSchema
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.82
     raiſ
    0.66
     незавершена
    0.64
     poffible
    0.62
    intios
    0.61
     autorytatywna
    0.60
     ſeveral
    0.57
     neceffary
    0.54
     виправивши
    0.54
     themſelves
    0.54
    Activations Density 4.058%

    No Known Activations