© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14621
    Prev
    Next
    INDEX
    Explanations

    words and phrases that enumerate a sequence of items or steps in an argument or explanation.

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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>
    -0.69
    huit
    -0.57
    endforeach
    -0.54
    queryInterface
    -0.54
    DaoImpl
    -0.53
    umesc
    -0.52
    []"
    -0.49
     الحره
    -0.49
    Portale
    -0.49
    ChildScrollView
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    1.00
    ftagPool
    0.83
    WebElementEntity
    0.74
    writeField
    0.69
    Hochspringen
    0.69
     通販
    0.68
    ArrowToggle
    0.66
    Naissance
    0.64
    DeleteBehavior
    0.60
     diſt
    0.59
    Activations Density 8.346%

    No Known Activations