© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11123
    Prev
    Next
    INDEX
    Explanations

    mentions of car manufacturers along with country and car model names.

    oai_token-act-pair · gemini-2.0-flash

    businesses and manufacturing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     agency
    -1.27
     agencies
    -1.26
     organizations
    -1.23
     institutions
    -1.23
     organisations
    -1.20
     organization
    -1.11
    agencies
    -1.09
     organisation
    -1.07
    institutions
    -1.06
    organizations
    -1.05
    POSITIVE LOGITS
    ToScroll
    0.38
    unk
    0.37
    toDouble
    0.36
     busto
    0.35
    职工
    0.35
    RDD
    0.35
    ertal
    0.35
    sendFile
    0.35
    clusal
    0.34
    +#+#
    0.34
    Activations Density 0.774%

    No Known Activations