© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1918
    Prev
    Next
    INDEX
    Explanations

    dates, non-English words, and terms from academic papers

    oai_token-act-pair · gemini-2.0-flash

    variety of text excerpts

    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
     QLabel
    -0.49
     lane
    -0.49
     propOrder
    -0.46
    AMO
    -0.44
    ificance
    -0.44
     due
    -0.44
    EME
    -0.43
    due
    -0.43
     désolés
    -0.43
    oye
    -0.43
    POSITIVE LOGITS
    TagMode
    0.84
     Audiodateien
    0.67
    Datuak
    0.63
    SpringBootTest
    0.63
    RepeatedField
    0.57
     épaules
    0.57
    Assured
    0.57
    :✨
    0.56
    httphttps
    0.56
    حياته
    0.55
    Activations Density 0.639%

    No Known Activations