© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4626
    Prev
    Next
    INDEX
    Explanations

    the reviewer's opinions, using phrases like "I think" or "I decided"

    oai_token-act-pair · gemini-2.0-flash

    streaming or watching content

    np_token-act-pair-logits · gpt-4o-mini

    streaming, watching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    awtextra
    -1.08
     propOrder
    -0.99
    ſelf
    -0.90
     myſelf
    -0.90
     Theſe
    -0.90
     itſelf
    -0.89
    thâu
    -0.89
     تضيفلها
    -0.88
     purpoſe
    -0.87
     ſy
    -0.87
    POSITIVE LOGITS
     stream
    0.64
     streaming
    0.56
     watch
    0.54
    stream
    0.53
     Watch
    0.52
     channel
    0.50
    Stream
    0.49
     ve
    0.49
    Watch
    0.49
    watch
    0.46
    Activations Density 1.710%

    No Known Activations