© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14911
    Prev
    Next
    INDEX
    Explanations

    uses the word "should"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    XmlAccessorType
    -0.74
     BoxDecoration
    -0.69
    DockStyle
    -0.68
     Theſe
    -0.67
     Amphi
    -0.67
    PMailer
    -0.66
    abestanden
    -0.65
    yship
    -0.64
     يتيمه
    -0.62
     ―――――
    -0.62
    POSITIVE LOGITS
     should
    1.19
     Should
    1.09
    should
    1.06
    Should
    1.04
     Shouldn
    0.92
     shouldn
    0.91
     SHOULD
    0.90
     devriez
    0.75
     sollte
    0.74
     sollten
    0.73
    Activations Density 1.647%

    No Known Activations