© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12637
    Prev
    Next
    INDEX
    Explanations

    words that indicate something is undesirable or wrong

    oai_token-act-pair · gemini-2.0-flash

    negative situations/affect

    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
    principalTable
    -0.62
     сожалению
    -0.54
    <()>
    -0.53
     plastiques
    -0.52
    providedIn
    -0.52
     initComponents
    -0.51
    OGND
    -0.50
     purtroppo
    -0.48
    esterno
    -0.47
     فريبيس
    -0.47
    POSITIVE LOGITS
    InputBorder
    0.68
    CloseOperation
    0.60
    Ici
    0.59
    جغرافيا
    0.55
    etration
    0.55
    clerview
    0.55
     needn
    0.54
    UpInside
    0.54
    不怕
    0.53
    WebVitals
    0.53
    Activations Density 2.042%

    No Known Activations