© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9438
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated content including code snippets, prices, and references to hot food

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     TextAppearance
    -0.55
     propOrder
    -0.51
     originais
    -0.50
    COMMERCIAL
    -0.49
     AsyncTask
    -0.46
    ️⃣
    -0.45
     lidí
    -0.45
    TestingModule
    -0.45
    .³
    -0.44
     zwierząt
    -0.44
    POSITIVE LOGITS
    ването
    0.60
    __(/*!
    0.60
    //
    0.60
     nahilalakip
    0.59
    вање
    0.59
    ъм
    0.58
    matchCondition
    0.57
     Belong
    0.57
     setw
    0.57
    endcsname
    0.57
    Activations Density 1.530%

    No Known Activations