© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5863
    Prev
    Next
    INDEX
    Explanations

    words relating to the concept of advancement or getting better

    oai_token-act-pair · gemini-2.0-flash

    upgrade

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ExecuteAsync
    -0.48
    magini
    -0.45
    SerializedName
    -0.44
    ModelAndView
    -0.44
     sztu
    -0.44
    otho
    -0.44
     Rond
    -0.43
     Kot
    -0.41
    Referències
    -0.41
    tola
    -0.41
    POSITIVE LOGITS
     upgrade
    1.58
    upgrade
    1.48
     upgrading
    1.45
     Upgrade
    1.43
     upgrades
    1.35
    Upgrade
    1.33
     upgraded
    1.33
     downgrade
    1.30
     Upgrades
    1.26
     upgra
    1.18
    Activations Density 1.357%

    No Known Activations