© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6102
    Prev
    Next
    INDEX
    Explanations

    words related to feelings, actions, and general sentiment

    oai_token-act-pair · gemini-2.0-flash

    emotional reactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     kepada
    -0.71
     NSCoder
    -0.66
     TextAlign
    -0.58
     kepad
    -0.58
     nahilalakip
    -0.56
    ToEnd
    -0.55
     vnto
    -0.52
     kaarangay
    -0.52
    alité
    -0.51
     إليها
    -0.50
    POSITIVE LOGITS
     us
    0.59
    IntoConstraints
    0.58
     calendriers
    0.58
     nonUne
    0.56
    ScopeManager
    0.55
     me
    0.52
    Portale
    0.51
     them
    0.48
    viewDidLoad
    0.47
    WebVitals
    0.46
    Activations Density 1.132%

    No Known Activations