© 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. 7146
    Prev
    Next
    INDEX
    Explanations

    sentences describing someone spending time doing a favorite activity

    oai_token-act-pair · gemini-2.0-flash

    Expectations

    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
    Hochspringen
    -0.51
    UrlResolution
    -0.51
    اظ
    -0.50
    رشف
    -0.49
     ddelweddau
    -0.49
    DispatchToProps
    -0.48
    iprot
    -0.47
    pulumi
    -0.47
     createStore
    -0.47
    AsUp
    -0.47
    POSITIVE LOGITS
     likely
    0.86
     Likely
    0.85
     Expect
    0.81
    likely
    0.79
    Expect
    0.77
    Likely
    0.75
     Chances
    0.70
     expect
    0.67
    expect
    0.66
     EXPECT
    0.65
    Activations Density 0.822%

    No Known Activations