© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    xml code and javascript code.

    oai_token-act-pair · gemini-2.0-flash

    start

    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
     start
    -2.19
    start
    -2.00
    Start
    -1.98
     Start
    -1.97
     starts
    -1.84
     begin
    -1.76
     START
    -1.68
     starting
    -1.63
    START
    -1.61
    starts
    -1.60
    POSITIVE LOGITS
    SBATCH
    0.82
    KURZBESCHREIBUNG
    0.77
     CascadeType
    0.77
    StructEnd
    0.76
    usercontent
    0.73
     IndexPath
    0.72
     kaarangay
    0.72
    SpringRunner
    0.71
    umoj
    0.70
    InjectAttribute
    0.70
    Activations Density 1.050%

    No Known Activations