© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12177
    Prev
    Next
    INDEX
    Explanations

    the word "off," especially as part of the phrase "trade-off"

    oai_token-act-pair · gemini-2.0-flash

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    off
    -2.66
    Off
    -2.50
     Off
    -2.36
    OFF
    -2.17
     off
    -2.14
    offs
    -1.99
     OFF
    -1.97
     offs
    -1.68
    オフ
    -1.49
     オフ
    -1.09
    POSITIVE LOGITS
    ônus
    0.59
     MainAxisSize
    0.59
    endsection
    0.58
    fastjson
    0.58
     objectForKey
    0.58
    SBATCH
    0.56
    useNewUrlParser
    0.56
    similiano
    0.56
    BURGH
    0.56
    QtGui
    0.55
    Activations Density 1.028%

    No Known Activations