© 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. 10092
    Prev
    Next
    INDEX
    Explanations

    transition words and grammatical constructs, many related to scientific or technical writing

    oai_token-act-pair · gemini-2.0-flash

    connecting words

    np_max-act · gemini-2.0-flash
    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
     تضيفلها
    -0.67
    ViewFeatures
    -0.61
     pinulongan
    -0.59
    islative
    -0.59
    hoeddwyd
    -0.58
    deauna
    -0.56
    hassee
    -0.56
    oredCriteria
    -0.55
     Shakspeare
    -0.55
    endphp
    -0.54
    POSITIVE LOGITS
    LabelTagHelper
    0.49
     huyền
    0.47
    SpringBootTest
    0.45
     BorderSide
    0.44
     SearchView
    0.44
    PickerController
    0.44
     solle
    0.43
     Sistemas
    0.43
     Scales
    0.43
    ahalli
    0.42
    Activations Density 4.290%

    No Known Activations