© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12591
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated terms potentially representing medical terms, programming code snippets and acronyms

    oai_token-act-pair · gemini-2.0-flash

    inspir

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    verifyException
    -0.68
     chaleur
    -0.65
     Wicidata
    -0.64
     occidentale
    -0.63
    transQ
    -0.63
     sociali
    -0.62
    wart
    -0.62
     Bucure
    -0.61
     vapeur
    -0.61
    RTGC
    -0.60
    POSITIVE LOGITS
     jScrollPane
    0.68
     I
    0.64
    withIdentifier
    0.62
     Icarus
    0.57
     iVar
    0.56
    iarkan
    0.55
    IInterface
    0.54
    acyj
    0.54
    Atoi
    0.54
     Fahrt
    0.52
    Activations Density 3.157%

    No Known Activations