© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8240
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to strong emotions or opinions

    oai_token-act-pair · gemini-2.0-flash

    Negative emotions/situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     cowardice
    -2.03
     throats
    -1.98
     virginity
    -1.92
     handcuffs
    -1.80
     martyrdom
    -1.79
     barbarians
    -1.76
     ingrat
    -1.75
     virgins
    -1.74
     pyjamas
    -1.73
     ashtray
    -1.72
    POSITIVE LOGITS
     be
    1.04
     of
    1.04
     to
    1.02
     w
    0.97
     with
    0.93
     for
    0.92
     that
    0.91
     pri
    0.90
     per
    0.90
     in
    0.90
    Activations Density 7.839%

    No Known Activations