© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11416
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to research and identification of factors

    oai_token-act-pair · gemini-2.0-flash

    identify

    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
     identify
    -1.84
     identification
    -1.71
     identifying
    -1.70
     identified
    -1.64
     identifies
    -1.57
     Identify
    -1.56
    identify
    -1.55
     Identifying
    -1.50
    Identify
    -1.50
     identity
    -1.49
    POSITIVE LOGITS
    DeleteBehavior
    0.85
    ArgsConstructor
    0.81
    ReusableCell
    0.70
     resourceCulture
    0.68
    DllImport
    0.62
     CreateTagHelper
    0.60
     مشين
    0.60
     versa
    0.60
     Roskov
    0.59
    IonicModule
    0.58
    Activations Density 7.360%

    No Known Activations