© 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. 5345
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to streets, cities, or counties, especially in Florida.

    oai_token-act-pair · gemini-2.0-flash

    Locations and Transportation

    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
    ControllerTest
    -0.57
    Identyfik
    -0.56
    tahui
    -0.54
    JspWriter
    -0.52
    bní
    -0.52
    σία
    -0.51
     typelib
    -0.50
    TargetException
    -0.50
    mockMvc
    -0.50
    huriyet
    -0.50
    POSITIVE LOGITS
     Roskov
    0.57
    WireFormatLite
    0.54
    :+:
    0.51
     Italijanski
    0.50
     ContentValues
    0.49
    EDEFAULT
    0.48
    katapos
    0.48
     Omni
    0.48
     Flag
    0.48
     chande
    0.48
    Activations Density 1.571%

    No Known Activations