© 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. 9663
    Prev
    Next
    INDEX
    Explanations

    words related to geography, especially place names and borders

    oai_token-act-pair · 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
    <bos>
    -0.50
    ratulations
    -0.48
    ʍ
    -0.41
     zufolge
    -0.40
    mpion
    -0.39
    chmal
    -0.39
     tranſ
    -0.39
    равда
    -0.38
    ntable
    -0.38
    IVEREF
    -0.36
    POSITIVE LOGITS
    MemoryWarning
    0.81
     HasFactory
    0.69
    stateMutability
    0.69
    IonicModule
    0.65
    ScopeManager
    0.65
    ThroughAttribute
    0.65
     PackageManager
    0.62
     الرياضيه
    0.62
    BeginInit
    0.62
    ResumeLayout
    0.62
    Activations Density 0.637%

    No Known Activations