© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3074
    Prev
    Next
    INDEX
    Explanations

    C++ output and input statements

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TagMode
    -0.72
    PreferredItem
    -0.71
    ValueStyle
    -0.64
    aarrggbb
    -0.64
    kháu
    -0.62
    djangoproject
    -0.59
     препратки
    -0.58
    WriteBarrier
    -0.58
     kasarigan
    -0.57
    -------------</
    -0.56
    POSITIVE LOGITS
    irical
    0.50
     percolation
    0.47
    éfono
    0.44
    المناصب
    0.43
    roppo
    0.43
    septic
    0.42
     leyendo
    0.42
     |=
    0.42
     Elgin
    0.42
     Outsourcing
    0.41
    Activations Density 0.576%

    No Known Activations