© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4531
    Prev
    Next
    INDEX
    Explanations

    code and code syntax

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis and Square Brackets

    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
    Negative Logits
    __":
    -0.77
     Shakspeare
    -0.74
    tableFuture
    -0.69
    __":
    -0.68
     Hopf
    -0.64
    __':
    -0.63
    BibitemShut
    -0.63
    VERTIS
    -0.63
    ^(@)
    -0.62
    __':
    -0.62
    POSITIVE LOGITS
    expandindo
    0.73
     distanciation
    0.57
    rungsseite
    0.55
     Chwiliwch
    0.53
     חיצוניים
    0.52
     استنادى
    0.52
     gynhyrchwyd
    0.50
     estekak
    0.49
     beginnetje
    0.48
    SizeF
    0.48
    Activations Density 4.527%

    No Known Activations