© 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. 5089
    Prev
    Next
    INDEX
    Explanations

    technical legal jargon related to privacy policies and warranties

    oai_token-act-pair · gemini-2.0-flash

    phrases related to privacy policies

    np_token-act-pair-logits · gpt-4o-mini
    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
     purpoſe
    -1.09
     myſelf
    -1.07
     ―――――
    -1.02
     itſelf
    -1.02
     raiſ
    -0.97
     fevere
    -0.94
     poffible
    -0.93
     auffi
    -0.93
     ſever
    -0.93
     pleaſure
    -0.92
    POSITIVE LOGITS
     from
    0.77
     
    0.74
     all
    0.71
     where
    0.71
     by
    0.65
    <eos>
    0.62
     Where
    0.62
     even
    0.61
    ↵
    0.60
    ↵↵
    0.60
    Activations Density 4.317%

    No Known Activations