© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7101
    Prev
    Next
    INDEX
    Explanations

    the word "title" or words that are very close

    oai_token-act-pair · gemini-2.0-flash

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     title
    -2.84
     Title
    -2.58
    Title
    -2.44
    title
    -2.36
     titles
    -2.34
     TITLE
    -2.17
     Titles
    -2.03
     Titel
    -1.99
    TITLE
    -1.98
     título
    -1.94
    POSITIVE LOGITS
     protoimpl
    0.64
    protoimpl
    0.58
     CreateTagHelper
    0.56
    WithIOException
    0.52
    Boletín
    0.51
     DriverManager
    0.51
    kuuta
    0.48
    FetchType
    0.46
    didSet
    0.44
     JOptionPane
    0.43
    Activations Density 0.391%

    No Known Activations