© 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. 11674
    Prev
    Next
    INDEX
    Explanations

    places in Hong Kong

    oai_token-act-pair · gemini-2.0-flash

    Hong Kong

    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
     EClass
    -0.65
    volent
    -0.59
     féd
    -0.59
    RectangleBorder
    -0.58
     fédéral
    -0.57
    CloseOperation
    -0.57
     nô
    -0.56
     fallu
    -0.56
    unknownFields
    -0.55
     fotografico
    -0.55
    POSITIVE LOGITS
    openzeppelin
    0.58
    BeginInit
    0.56
    ForRow
    0.55
    ToTensor
    0.49
    interopRequire
    0.47
    νώ
    0.46
     output
    0.46
     cục
    0.45
    migrationBuilder
    0.45
    ạch
    0.44
    Activations Density 0.030%

    No Known Activations