© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11001
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly Javascript and PHP, involving AJAX calls and JSON data

    oai_token-act-pair · gemini-2.0-flash

    post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    хьтан
    -0.54
    wanna
    -0.50
    SerializedName
    -0.49
    OrNil
    -0.47
     صوتيه
    -0.47
     wanna
    -0.45
    <>
    -0.43
    ExtendWith
    -0.43
    ">//
    -0.43
     redor
    -0.41
    POSITIVE LOGITS
     féminine
    0.83
    SequentialGroup
    0.73
     continúas
    0.70
     étrangère
    0.68
     ujednoznacz
    0.66
    τως
    0.66
     ainfi
    0.66
    ніципалі
    0.65
    BeginContext
    0.65
    Orsay
    0.64
    Activations Density 2.044%

    No Known Activations