© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3680
    Prev
    Next
    INDEX
    Explanations

    words related to parenting and children

    oai_token-act-pair · gemini-2.0-flash

    children/babies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    timmung
    -0.53
    tabular
    -0.52
     Signalez
    -0.51
     TextInputType
    -0.48
     initComponents
    -0.48
     JpaRepository
    -0.48
    Team
    -0.47
    team
    -0.47
    withstanding
    -0.46
    Réalisation
    -0.45
    POSITIVE LOGITS
     BIBSYS
    0.58
     Roskov
    0.57
    ArrowToggle
    0.55
    Šaltiniai
    0.54
    RTHOOK
    0.54
     alimentaires
    0.53
     ouvriers
    0.53
    Дереккөздер
    0.51
    Atsauces
    0.50
     balls
    0.50
    Activations Density 2.968%

    No Known Activations