© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4580
    Prev
    Next
    INDEX
    Explanations

    code or identifiers that include the word "type"

    oai_token-act-pair · gemini-2.0-flash

    type

    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
    Negative Logits
    Type
    -2.03
     Type
    -1.91
     type
    -1.83
    type
    -1.73
    TYPE
    -1.50
     TYPE
    -1.49
     types
    -1.38
     tipo
    -1.30
     Types
    -1.28
    类型
    -1.27
    POSITIVE LOGITS
    IntoConstraints
    0.65
    featureID
    0.63
    findpost
    0.62
    flink
    0.58
    Sucesor
    0.56
    fjspx
    0.55
     mattino
    0.54
    osó
    0.53
     الحره
    0.52
    CppMethod
    0.52
    Activations Density 2.215%

    No Known Activations