© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15691
    Prev
    Next
    INDEX
    Explanations

    words which describe people in organizations or in groups helping others

    oai_token-act-pair · gemini-2.0-flash

    Work environments and staff

    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
     pulumi
    -0.56
    RetentionPolicy
    -0.52
    __':
    
    -0.52
    KURZBESCHREIBUNG
    -0.52
    RTLI
    -0.51
     />);
    -0.50
     setShow
    -0.47
    jgl
    -0.47
     Pech
    -0.46
     firebaseConfig
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.61
     otomatig
    0.57
    
    0.56
    日閲覧
    0.56
     séparation
    0.54
    DotNetBar
    0.53
    decorator
    0.53
    UrlResolution
    0.52
     generalization
    0.51
    NameInMap
    0.51
    Activations Density 4.109%

    No Known Activations