© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15143
    Prev
    Next
    INDEX
    Explanations

    the word "the" (with slight variance based on context)

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     is
    -0.42
     the
    -0.42
     et
    -0.41
     mit
    -0.41
     a
    -0.40
    ContentLoaded
    -0.39
     referirse
    -0.39
    jalankan
    -0.37
     M
    -0.36
     proviene
    -0.36
    POSITIVE LOGITS
     purpoſe
    0.98
    Diweddarwch
    0.96
    ſelf
    0.92
     greateſt
    0.90
     diſt
    0.90
     themſelves
    0.86
     ſtate
    0.86
     quæ
    0.85
     ſever
    0.85
     ſeveral
    0.84
    Activations Density 2.656%

    No Known Activations