© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4725
    Prev
    Next
    INDEX
    Explanations

    facts and sources in an article, but also seems to key on transitional words and phrases

    oai_token-act-pair · gemini-2.0-flash

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     I
    -0.54
    …
    -0.49
     terk
    -0.45
    !
    -0.44
     :
    -0.43
     car
    -0.43
    ...
    -0.42
     (
    -0.42
     Car
    -0.42
    ..
    -0.42
    POSITIVE LOGITS
     تضيفلها
    1.03
     Efq
    0.96
     Jefus
    0.96
     myſelf
    0.96
     Majefty
    0.91
     itſelf
    0.91
     onOptions
    0.90
    afficheront
    0.89
     Monfieur
    0.89
    ImageContext
    0.87
    Activations Density 0.514%

    No Known Activations