© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11756
    Prev
    Next
    INDEX
    Explanations

    sentences where the author is reflecting on personal experiences

    oai_token-act-pair · gemini-2.0-flash

    Sewing and clothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    elemField
    -0.65
     незавершена
    -0.64
    اریخ
    -0.53
    principalTable
    -0.52
    windowFixed
    -0.49
    matchCondition
    -0.48
     ?";
    -0.47
     препратки
    -0.46
     يتيمه
    -0.46
    nodoc
    -0.45
    POSITIVE LOGITS
     people
    0.64
     initComponents
    0.63
     nôtre
    0.57
     SqlParameter
    0.55
     persons
    0.55
     personne
    0.54
    izienz
    0.54
     students
    0.54
    people
    0.54
    IsContent
    0.54
    Activations Density 2.231%

    No Known Activations