© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10869
    Prev
    Next
    INDEX
    Explanations

    numerical data, phone numbers, and gaze with the word met.

    oai_token-act-pair · gemini-2.0-flash

    Formatted data/lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    onAttach
    -0.52
     betweenstory
    -0.50
     Paglinawan
    -0.46
    createNewFile
    -0.43
    ыгана
    -0.42
    principalColumn
    -0.40
     répond
    -0.40
     setUp
    -0.39
    OGND
    -0.38
    lope
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.70
     estekak
    0.65
    новниш
    0.61
    endpush
    0.59
    ArgsConstructor
    0.57
    RetentionPolicy
    0.56
    awtextra
    0.56
    ModelSerializer
    0.55
     AspNetCore
    0.55
     فريبيس
    0.53
    Activations Density 1.594%

    No Known Activations