© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13042
    Prev
    Next
    INDEX
    Explanations

    the word "thought" and related words of consideration

    oai_token-act-pair · gemini-2.0-flash

    thought

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.08
    IntoConstraints
    -0.96
    SEGUIR
    -0.82
     Monfieur
    -0.79
     uſed
    -0.79
    BeginInit
    -0.78
     leaſt
    -0.77
    ausea
    -0.76
     cauſe
    -0.75
     Reſ
    -0.75
    POSITIVE LOGITS
     in
    0.66
     
    0.57
     on
    0.56
     specialising
    0.56
     with
    0.55
     specialises
    0.55
     specialise
    0.54
    ,
    0.50
    dziew
    0.50
    <eos>
    0.50
    Activations Density 0.286%

    No Known Activations