© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5778
    Prev
    Next
    INDEX
    Explanations

    the phrase "Continue Reading"

    oai_token-act-pair · gemini-2.0-flash

    website article excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    <bos>
    -0.74
    co
    -0.61
    qu
    -0.60
     ${
    -0.59
    ori
    -0.58
    oo
    -0.56
    c
    -0.56
    ,
    -0.55
    lu
    -0.55
    ny
    -0.55
    POSITIVE LOGITS
     Theſe
    0.85
     myſelf
    0.84
    ^(@)
    0.80
     becauſe
    0.80
     Efq
    0.79
     Majefty
    0.76
     pleaſure
    0.75
     itſelf
    0.75
     Chriftian
    0.74
     Monfieur
    0.72
    Activations Density 5.088%

    No Known Activations