© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    code with special characters for math and computer languages

    oai_token-act-pair · gemini-2.0-flash

    mixed text and symbols

    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
     TT
    -1.24
     TC
    -1.20
     TS
    -1.19
     TG
    -1.16
     TMC
    -1.16
     TB
    -1.14
     TN
    -1.13
     TM
    -1.13
     TK
    -1.12
     TP
    -1.11
    POSITIVE LOGITS
    chenden
    0.37
    afficheront
    0.37
    CodeDom
    0.34
     viện
    0.34
    krivning
    0.33
    フィシャル
    0.33
    pagestyle
    0.33
     Vương
    0.33
    ühm
    0.32
     lò
    0.32
    Activations Density 52.442%

    No Known Activations