© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    location names with street addresses and events celebrating local people

    oai_token-act-pair · gemini-2.0-flash

    New York references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    NY
    -0.58
     Manhattan
    -0.57
     Harlem
    -0.54
     NY
    -0.52
     brooklyn
    -0.50
     NYPD
    -0.50
    olyte
    -0.50
     NYC
    -0.48
     supernova
    -0.48
    Manhattan
    -0.48
    POSITIVE LOGITS
    ьаж
    0.84
    MigrationBuilder
    0.73
    はじめに
    0.68
    DataAnnotations
    0.67
    InstanceState
    0.65
    +#+#
    0.64
    MessageTagHelper
    0.59
    WireFormatLite
    0.58
     numerus
    0.58
    Rüyada
    0.56
    Activations Density 1.229%

    No Known Activations