© 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. 13822
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary, potentially related to medicine, genetics, and programming.

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific texts

    np_max-act · gemini-2.0-flash

    relationship

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    bler
    -0.50
     Fasc
    -0.49
     dager
    -0.48
    enskap
    -0.47
     dacia
    -0.46
    uruh
    -0.46
     Bellamy
    -0.46
    POUR
    -0.46
    ũng
    -0.45
     hemis
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.77
    URLException
    0.74
    writeField
    0.64
     beginnetje
    0.64
    Geplaatst
    0.63
    ItemBackground
    0.61
     typelib
    0.60
     AssemblyCulture
    0.60
    abestanden
    0.56
    MemoryWarning
    0.56
    Activations Density 8.320%

    No Known Activations