© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4605
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to XML

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ContentValues
    -0.59
     bref
    -0.58
     UITableView
    -0.57
     Metzger
    -0.56
     Haber
    -0.55
     cauſe
    -0.55
    TestingModule
    -0.54
     Zweig
    -0.54
    chua
    -0.54
     dreamstime
    -0.53
    POSITIVE LOGITS
     חיצוניים
    0.57
    styleType
    0.49
    localctx
    0.49
    Statics
    0.48
    Dynamic
    0.44
    dynamic
    0.43
     arru
    0.41
    optim
    0.41
    ET
    0.41
    ostruct
    0.41
    Activations Density 0.674%

    No Known Activations