© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9887
    Prev
    Next
    INDEX
    Explanations

    places, especially cities and states, and sports terms

    oai_token-act-pair · gemini-2.0-flash

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Personensuche
    -0.80
    
    -0.65
     EconPapers
    -0.60
    IndentedString
    -0.58
     cristian
    -0.54
     keel
    -0.54
    ScopeManager
    -0.54
    contentLoaded
    -0.52
    LocalizedString
    -0.52
     esboço
    -0.52
    POSITIVE LOGITS
    <bos>
    0.72
    oneof
    0.56
     Roskov
    0.54
    SequentialGroup
    0.54
     uska
    0.53
    titled
    0.53
     mxArray
    0.53
    onin
    0.49
    TRIBUN
    0.48
    celes
    0.46
    Activations Density 11.329%

    No Known Activations