© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6580
    Prev
    Next
    INDEX
    Explanations

    first-person references related to experience

    oai_token-act-pair · gemini-2.0-flash

    No clear pattern found in other methods, default explanation.Having

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     wouldn
    -0.75
    wouldn
    -0.59
     would
    -0.55
     trade
    -0.53
     wouldnt
    -0.52
     Wouldn
    -0.51
     Trade
    -0.51
     Would
    -0.49
    Trade
    -0.49
    trade
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.74
    fillType
    0.68
    SpringBootTest
    0.65
    sizeCache
    0.63
    WireFormat
    0.62
    NameInMap
    0.62
    findpost
    0.60
    TagHelper
    0.59
     **)
    0.54
     ligiloj
    0.54
    Activations Density 1.326%

    No Known Activations