© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3626
    Prev
    Next
    INDEX
    Explanations

    hypothetical statements, especially those using "would rather"

    oai_token-act-pair · gemini-2.0-flash

    Expressing preferences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     would
    -0.83
    would
    -0.77
     wouldn
    -0.73
     Would
    -0.70
    Would
    -0.69
     WOULD
    -0.69
    wouldn
    -0.65
     Wouldn
    -0.63
    Wouldn
    -0.62
     wouldnt
    -0.56
    POSITIVE LOGITS
     مرئيه
    0.71
    oredCriteria
    0.68
     MessageBoxIcon
    0.65
    fillType
    0.59
     utafitiHapana
    0.59
     FetchType
    0.57
    potranspiration
    0.54
    AutoField
    0.54
    RenderAtEndOf
    0.53
    “……”
    0.52
    Activations Density 1.620%

    No Known Activations