© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3666
    Prev
    Next
    INDEX
    Explanations

    words that indicate uncertainty, caveats, or politeness

    oai_token-act-pair · gemini-2.0-flash

    words indicating contrast or exception

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

    though/although

    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
    "><!--
    -0.41
    >>();
    -0.41
    っか
    -0.39
    琥
    -0.37
    "}")
    -0.37
    ση
    -0.37
    σης
    -0.36
    mel
    -0.36
    уда
    -0.36
    querySelector
    -0.36
    POSITIVE LOGITS
     referenties
    0.86
     Jefus
    0.84
     myſelf
    0.83
     they
    0.81
     reaſon
    0.79
     الرياضيه
    0.77
     themſelves
    0.77
     iſt
    0.77
    ValueStyle
    0.75
     Monfieur
    0.75
    Activations Density 3.534%

    No Known Activations