© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5071
    Prev
    Next
    INDEX
    Explanations

    code related to Github URLs

    oai_token-act-pair · gemini-2.0-flash

    github

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    github
    -1.84
     github
    -1.32
     GitHub
    -1.13
     Github
    -1.10
    GitHub
    -1.03
    Github
    -1.03
    GITHUB
    -0.79
    gitlab
    -0.78
    git
    -0.71
     CURIAM
    -0.69
    POSITIVE LOGITS
     rospy
    0.64
     StatefulWidget
    0.63
     propOrder
    0.58
     geleverd
    0.55
    发表于
    0.53
     متعلقه
    0.52
     betweenstory
    0.52
    mphony
    0.52
    SourceChecksum
    0.51
    GEBURTSDATUM
    0.48
    Activations Density 0.085%

    No Known Activations