© 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. 229
    Prev
    Next
    INDEX
    Explanations

    words related to coding errors using Maven, Java, and Apache

    oai_token-act-pair · gemini-2.0-flash

    Foreign language text

    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
     houſe
    -1.04
     whoſe
    -0.96
     purpoſe
    -0.94
     pleaſure
    -0.93
     himſelf
    -0.93
     Diſ
    -0.91
     avoient
    -0.91
     ſtre
    -0.91
     ſta
    -0.89
     ſtand
    -0.89
    POSITIVE LOGITS
    :+:
    0.56
    IPAC
    0.55
     Ste
    0.55
    "];
    0.54
     gql
    0.53
     gradova
    0.53
     onData
    0.53
    TabIndex
    0.52
    Vidite
    0.51
    "]
    0.51
    Activations Density 8.060%

    No Known Activations