© 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. 8407
    Prev
    Next
    INDEX
    Explanations

    code snippets along with the words "assert", "query," "candidate," "list," and/or "broader".

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     equals
    -0.72
    )==
    -0.71
    EDEFAULT
    -0.70
     equal
    -0.67
     coincides
    -0.66
    
    -0.65
     coincide
    -0.65
    EqualTo
    -0.65
    equal
    -0.65
    正是
    -0.64
    POSITIVE LOGITS
     Italijani
    0.56
     nonzero
    0.56
     distinto
    0.51
    tableFuture
    0.51
     khác
    0.51
    Distinct
    0.50
     diferente
    0.50
     ≠
    0.50
     non
    0.50
     differ
    0.49
    Activations Density 1.546%

    No Known Activations