© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9778
    Prev
    Next
    INDEX
    Explanations

    phrases of discourse such as "Despite" or "due to"

    oai_token-act-pair · gemini-2.0-flash

    despite

    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
    It
    -0.49
    We
    -0.44
    '
    -0.43
    -
    -0.40
    vi
    -0.40
    If
    -0.40
    I
    -0.39
    <eos>
    -0.38
    There
    -0.36
    ’
    -0.36
    POSITIVE LOGITS
     myſelf
    1.23
     the
    1.19
     Efq
    1.15
     itſelf
    1.13
     themſelves
    1.11
     himſelf
    1.10
     Jefus
    1.09
     Monfieur
    1.09
     whoſe
    1.05
     reaſon
    1.05
    Activations Density 12.717%

    No Known Activations