© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9253
    Prev
    Next
    INDEX
    Explanations

    personal pronouns relating positive sentiments and desires

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    存于互联网档案馆
    -0.55
     ISNI
    -0.48
    CppMethod
    -0.47
    DeleteBehavior
    -0.44
    AccessorTable
    -0.44
    InjectAttribute
    -0.44
     /\.
    -0.43
     AttributeSet
    -0.43
    )!=
    -0.43
    ChildScrollView
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.95
    lej
    0.57
    simpleType
    0.57
    otsu
    0.56
    ορ
    0.56
     ujednoznacz
    0.54
    पन
    0.54
    脚注の使い方
    0.54
    yped
    0.54
    iller
    0.52
    Activations Density 3.407%

    No Known Activations