© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14316
    Prev
    Next
    INDEX
    Explanations

    words relating to obligation, especially how things will be or must be

    oai_token-act-pair · gemini-2.0-flash

    programming code

    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
     kaarangay
    -0.72
    ValueStyle
    -0.63
     faced
    -0.54
     utafitiHapana
    -0.54
     Experiences
    -0.54
     suffering
    -0.53
    -------------</
    -0.52
     Faced
    -0.51
     experiences
    -0.50
     Suffering
    -0.50
    POSITIVE LOGITS
    crollView
    0.58
    niająca
    0.57
    ReusableCell
    0.53
    roek
    0.51
     useRouter
    0.51
    ตรง
    0.50
    SharedDtor
    0.49
     ComVisible
    0.48
    wapV
    0.48
    modelBuilder
    0.46
    Activations Density 8.176%

    No Known Activations