© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8306
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to military conflict, political occupation and geographical locations

    oai_token-act-pair · gemini-2.0-flash

    portions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     autorytatywna
    -0.62
    StructEnd
    -0.60
    principalColumn
    -0.59
     disambiguazione
    -0.59
    MemoryWarning
    -0.56
    MODO
    -0.54
     nahilalakip
    -0.53
     surla
    -0.52
     rupiah
    -0.50
     Muhammadu
    -0.49
    POSITIVE LOGITS
     parts
    1.32
     entire
    1.11
     portions
    1.10
    parts
    1.07
     part
    1.07
     Parts
    1.06
    Parts
    1.03
     whole
    1.02
     PARTS
    0.99
    whole
    0.96
    Activations Density 1.406%

    No Known Activations