© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8147
    Prev
    Next
    INDEX
    Explanations

    source code, mathematical notation, and file paths/references

    oai_token-act-pair · gemini-2.0-flash

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ^(@)
    -0.65
     Monfieur
    -0.64
     myſelf
    -0.63
     Efq
    -0.52
    ]--;
    -0.52
    chenkt
    -0.51
     doubtnut
    -0.50
     uſe
    -0.50
     juſ
    -0.50
     Eſ
    -0.50
    POSITIVE LOGITS
    :✨
    0.74
    InvalidProtocol
    0.71
    esgue
    0.62
     nakalista
    0.61
    Santis
    0.60
    GEBURTSDATUM
    0.57
    /*++
    0.57
    TestingModule
    0.57
     localObject
    0.56
    جوايز
    0.54
    Activations Density 3.931%

    No Known Activations