© 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. 4231
    Prev
    Next
    INDEX
    Explanations

    the string "re" indicating it might be detecting words with the prefix "re"

    oai_token-act-pair · gemini-2.0-flash

    Re

    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
    audiovisuel
    -0.66
    OGND
    -0.59
    Filmografie
    -0.58
    eradish
    -0.58
     clans
    -0.57
     TimeUnit
    -0.56
     Mev
    -0.55
    ;->
    -0.54
    XmlType
    -0.53
     getRule
    -0.53
    POSITIVE LOGITS
    通販
    0.56
    IntoConstraints
    0.54
    TagHelper
    0.53
     originali
    0.53
    WebServlet
    0.53
     nacionais
    0.52
     internacionais
    0.50
     orígenes
    0.50
     laterales
    0.50
    aarrggbb
    0.50
    Activations Density 1.245%

    No Known Activations