© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10550
    Prev
    Next
    INDEX
    Explanations

    substrings often appearing in markup and programming languages

    oai_token-act-pair · gemini-2.0-flash

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    rungsseite
    -0.65
     DbSet
    -0.65
    ⓘ
    -0.65
    GEBURTS
    -0.65
    rrggbb
    -0.55
    :✨
    -0.55
    StoryboardSegue
    -0.55
    urtstag
    -0.53
    rofoam
    -0.53
    FieldBuilder
    -0.52
    POSITIVE LOGITS
     Cæsar
    0.59
     fidèles
    0.56
     Molière
    0.56
    )$/,
    0.55
     perla
    0.52
     Shakspeare
    0.52
    ligheten
    0.52
     bulundu
    0.51
     Eto
    0.50
     relacionado
    0.50
    Activations Density 0.594%

    No Known Activations