© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15617
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are joining two terms like and/or, or things in parenthesis

    oai_token-act-pair · gemini-2.0-flash

    technical terminology and identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     WQS
    -0.49
    AOC
    -0.49
     ESR
    -0.49
     AIA
    -0.48
     AOC
    -0.47
     ATS
    -0.46
     ICC
    -0.46
    Jäh
    -0.45
     PMC
    -0.45
     ACS
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.82
     Efq
    0.74
    Autoritní
    0.73
     незавершена
    0.69
    Geplaatst
    0.68
     NDEBUG
    0.68
     Theſe
    0.68
    fromCharCode
    0.66
     RISERV
    0.66
     VARIABLE
    0.66
    Activations Density 2.918%

    No Known Activations