© 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. 2470
    Prev
    Next
    INDEX
    Explanations

    family relationships and activities

    oai_token-act-pair · gemini-2.0-flash

    names of children

    np_token-act-pair-logits · gpt-4o-mini
    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
     RouterModule
    -0.59
    lapsingToolbar
    -0.53
     Kathy
    -0.51
    shid
    -0.50
    Steve
    -0.50
     Steve
    -0.49
    didSet
    -0.49
    Kathy
    -0.47
    存于互联网档案馆
    -0.47
     enfans
    -0.47
    POSITIVE LOGITS
     Ava
    0.87
    Ava
    0.78
     Avery
    0.76
     Finn
    0.72
     Harlow
    0.68
    Finn
    0.64
     StatelessWidget
    0.63
     Carter
    0.62
    FormTagHelper
    0.62
     Maximus
    0.61
    Activations Density 1.613%

    No Known Activations