© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2776
    Prev
    Next
    INDEX
    Explanations

    short words such as prepositions or articles

    oai_token-act-pair · gemini-2.0-flash

    "at"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    NameInMap
    -0.58
    AsUp
    -0.58
    ReusableCell
    -0.57
    medriver
    -0.56
    PerformLayout
    -0.54
    orteur
    -0.52
     GenerationType
    -0.50
    SpringBootTest
    -0.49
    EDEFAULT
    -0.49
    hawatir
    -0.47
    POSITIVE LOGITS
     at
    3.14
    at
    1.88
    At
    1.77
     At
    1.70
     tại
    1.54
     atx
    1.05
    Tại
    1.02
     AT
    1.02
    AtIndex
    0.98
     	e
    0.96
    Activations Density 17.971%

    No Known Activations