© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10946
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to emotional states, particularly happiness, sadness, and being recognized, especially in conjunction with the verb "to be."

    oai_token-act-pair · gemini-2.0-flash

    desired state

    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
     initComponents
    -0.68
    itinéraire
    -0.54
    Aiheesta
    -0.52
    SourceChecksum
    -0.52
    validates
    -0.52
     ejerc
    -0.50
     costi
    -0.50
     confronti
    -0.50
     }}}{
    -0.49
    InjectAttribute
    -0.49
    POSITIVE LOGITS
     wanted
    1.80
    wanted
    1.42
     Wanted
    1.32
     needed
    1.30
    needed
    1.18
    Wanted
    1.13
     Needed
    1.13
     WANTED
    1.02
     NEEDED
    0.94
     desired
    0.90
    Activations Density 2.578%

    No Known Activations