© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1411
    Prev
    Next
    INDEX
    Explanations

    family relationships and people at work

    oai_token-act-pair · gemini-2.0-flash

    in-laws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    }],
    -0.56
     indipendente
    -0.55
     assinatura
    -0.55
    ynb
    -0.53
    GridColumn
    -0.51
     frequenza
    -0.48
    setObjectName
    -0.48
    Sklici
    -0.48
     scurt
    -0.47
     "..\..\
    -0.46
    POSITIVE LOGITS
     Couples
    0.72
     divorced
    0.69
     couples
    0.69
    weds
    0.69
     married
    0.65
    Gambas
    0.65
     spouses
    0.65
     Wives
    0.63
     AspNetCore
    0.63
     family
    0.61
    Activations Density 1.123%

    No Known Activations