© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9822
    Prev
    Next
    INDEX
    Explanations

    words associated with the context of official studies or reports.

    oai_token-act-pair · gemini-2.0-flash

    terms related to vulnerable populations

    np_token-act-pair-logits · gpt-4o-mini

    children and vulnerable populations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    stdc
    -0.69
     Theſe
    -0.66
     (\<
    -0.64
    StoreMessageInfo
    -0.63
     extérieure
    -0.63
    IBOutlet
    -0.62
     photolibrary
    -0.62
    ^(@)
    -0.61
    ;%%
    -0.60
    rawValue
    -0.60
    POSITIVE LOGITS
    min
    0.52
     male
    0.51
     vulnerable
    0.50
     elle
    0.48
     unknow
    0.48
     <<<<<<<<<<<<<<
    0.47
     susceptible
    0.47
     disadvantaged
    0.46
     diss
    0.46
     thousands
    0.46
    Activations Density 5.382%

    No Known Activations