© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8080
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ma', especially 'Martin', and parts of the name 'Aberforth'

    oai_token-act-pair · gemini-2.0-flash

    ma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ma
    -2.09
    MA
    -1.38
    maa
    -0.82
    ма
    -0.82
    mma
    -0.80
    EMA
    -0.78
    OMA
    -0.75
    mab
    -0.75
    maf
    -0.73
    Portail
    -0.71
    POSITIVE LOGITS
     بيها
    0.61
    NameInMap
    0.59
     CURIAM
    0.56
    اعده
    0.53
    
    0.52
     Tapia
    0.50
     collision
    0.46
    collision
    0.46
     يتيمه
    0.45
    MERGE
    0.45
    Activations Density 0.358%

    No Known Activations