© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3941
    Prev
    Next
    INDEX
    Explanations

    the word "quite", along with words that appear near or with it

    oai_token-act-pair · gemini-2.0-flash

    quite

    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
     Houſe
    -1.44
     Diſ
    -1.37
     Reſ
    -1.28
     Anſ
    -1.24
     pleaſure
    -1.20
     houſe
    -1.19
     Conſ
    -1.18
     Jefus
    -1.15
     Theſe
    -1.14
     Perſ
    -1.13
    POSITIVE LOGITS
     an
    0.74
     a
    0.73
     am
    0.66
     (
    0.65
     
    0.63
    -
    0.62
     A
    0.62
     all
    0.61
     in
    0.59
     the
    0.59
    Activations Density 1.267%

    No Known Activations