© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11645
    Prev
    Next
    INDEX
    Explanations

    place names, particularly Atlanta and Seattle

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.41
    Atlanta
    -0.60
    Toronto
    -0.56
     Atlanta
    -0.55
    Chicago
    -0.54
    ↵↵
    -0.54
    Houston
    -0.53
    I
    -0.53
    Seattle
    -0.52
    Tampa
    -0.50
    POSITIVE LOGITS
     مشين
    0.81
    RenderAtEndOf
    0.81
     متعلقه
    0.81
     pinulongan
    0.76
     altrett
    0.68
    abestanden
    0.68
    逅
    0.68
    ruptedException
    0.67
    AutoresizingMask
    0.67
    secutive
    0.66
    Activations Density 0.733%

    No Known Activations