© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6439
    Prev
    Next
    INDEX
    Explanations

    phrases about looking, seeing, and finding things

    oai_token-act-pair · gemini-2.0-flash

    "in" in other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    urlpatterns
    -0.72
     FetchType
    -0.69
    DockStyle
    -0.68
     defaultstate
    -0.63
     jScrollPane
    -0.59
     szóci
    -0.59
    MigrationBuilder
    -0.59
    writeFieldEnd
    -0.59
    Personensuche
    -0.58
    
    -0.57
    POSITIVE LOGITS
     in
    1.48
    ใน
    0.90
    InThe
    0.88
     في
    0.84
    inthe
    0.83
     в
    0.81
     در
    0.69
     dalam
    0.68
     în
    0.65
     trong
    0.63
    Activations Density 3.785%

    No Known Activations