© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11838
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to locations and transportation

    oai_token-act-pair · gemini-2.0-flash

    city centers, capitals

    np_max-act · gemini-2.0-flash

    city locations Method used: 1 — because max tokens denote urban/place terms

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Kick
    -0.50
     Kick
    -0.48
     kick
    -0.48
    kick
    -0.46
    ով
    -0.44
    НИК
    -0.42
    MigrationBuilder
    -0.40
     estekak
    -0.40
    راد
    -0.39
    diente
    -0.39
    POSITIVE LOGITS
     himſelf
    0.74
    庁
    0.69
    GEBURTS
    0.69
     downtown
    0.66
     aeropuerto
    0.65
     itſelf
    0.65
     InputDecoration
    0.64
    CloseOperation
    0.63
    ächtig
    0.63
     AssemblyCompany
    0.63
    Activations Density 1.004%

    No Known Activations