© 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. 9872
    Prev
    Next
    INDEX
    Explanations

    locations, particularly cities and states within the United States

    oai_token-act-pair · gemini-2.0-flash

    city names

    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
    
    -0.94
    DeleteBehavior
    -0.93
    rungsseite
    -0.84
     Roskov
    -0.76
     estekak
    -0.75
     Infórmanos
    -0.75
    MigrationBuilder
    -0.75
    ViewFeatures
    -0.75
    клопе
    -0.74
     CallOverrides
    -0.73
    POSITIVE LOGITS
     man
    0.49
    bootstrapcdn
    0.48
     Ready
    0.46
     Block
    0.44
     Schaff
    0.42
    halle
    0.40
    READY
    0.40
     Man
    0.40
     MAN
    0.40
    Ready
    0.39
    Activations Density 1.235%

    No Known Activations