© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5470
    Prev
    Next
    INDEX
    Explanations

    the words "forth" or "back" and words surrounding them

    oai_token-act-pair · gemini-2.0-flash

    movement

    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
     AssemblyCulture
    -0.54
    <bos>
    -0.54
     يتيمه
    -0.52
     rispet
    -0.49
     hukuman
    -0.48
    让他们
    -0.48
    Приятного
    -0.46
     observación
    -0.45
     reír
    -0.45
     auttaa
    -0.44
    POSITIVE LOGITS
     propOrder
    0.85
    ChildScrollView
    0.85
     JpaRepository
    0.81
    Hochspringen
    0.75
     EconPapers
    0.73
     consultato
    0.70
    Parcelize
    0.69
    SerializedName
    0.69
    onViewCreated
    0.69
    RegressionTest
    0.68
    Activations Density 0.860%

    No Known Activations