© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14940
    Prev
    Next
    INDEX
    Explanations

    a context where a state, being, or process is happening.

    oai_token-act-pair · gemini-2.0-flash

    be

    np_max-act-logits · gemini-2.0-flash

    be

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     igång
    -0.55
     möjligt
    -0.54
     Grown
    -0.54
     Starting
    -0.53
     morire
    -0.52
     navnet
    -0.52
     hjälp
    -0.50
     citoyens
    -0.50
     iniciales
    -0.50
     Púb
    -0.49
    POSITIVE LOGITS
    
    0.77
     EconPapers
    0.75
    .[/
    0.64
    afficheront
    0.63
    migrationBuilder
    0.62
    complexContent
    0.58
    QMetaType
    0.57
    ɵɵ
    0.57
    reportWebVitals
    0.54
     onCancelled
    0.54
    Activations Density 31.166%

    No Known Activations