© 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. 11952
    Prev
    Next
    INDEX
    Explanations

    the word "beyond" and words that are closely associated with it

    oai_token-act-pair · gemini-2.0-flash

    beyond

    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
     the
    -0.96
     a
    -0.91
     
    -0.78
     some
    -0.78
     "
    -0.76
     '
    -0.76
     all
    -0.75
     \
    -0.73
    <eos>
    -0.73
     so
    -0.73
    POSITIVE LOGITS
     itſelf
    1.76
     Efq
    1.58
     myſelf
    1.54
     Majefty
    1.42
     himſelf
    1.41
     themſelves
    1.38
     Houſe
    1.33
     Anſ
    1.32
     ſhe
    1.32
     Shakspeare
    1.29
    Activations Density 3.429%

    No Known Activations