© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10229
    Prev
    Next
    INDEX
    Explanations

    something related to a multi-step plan or process containing multiple parts

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    luß
    -0.68
    Whilst
    -0.67
     Whilst
    -0.65
     poichè
    -0.57
    の為
    -0.57
     Amongst
    -0.56
     &
    -0.55
     perchè
    -0.55
     diatas
    -0.54
     whilst
    -0.54
    POSITIVE LOGITS
     lenker
    0.78
     Audiodateien
    0.75
    Lähteet
    0.71
    ◗
    0.69
     >=",
    0.68
     cherchés
    0.67
    : 
    0.67
    таратура
    0.66
    !*\
    0.65
     disambiguazione
    0.64
    Activations Density 20.359%

    No Known Activations