© 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. 10266
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "SU"

    oai_token-act-pair · gemini-2.0-flash

    su

    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
    Su
    -2.58
    su
    -2.50
     Su
    -2.45
     su
    -2.36
    SU
    -1.95
     SU
    -1.88
     Су
    -1.06
    suz
    -1.05
     су
    -1.05
    Су
    -0.99
    POSITIVE LOGITS
     estekak
    0.72
    homonymie
    0.71
     HasFactory
    0.71
     purpoſe
    0.68
     '{@
    0.68
     nakalista
    0.66
    jspx
    0.65
    ValueGeneration
    0.65
    İstinadlar
    0.65
    verwijspagina
    0.64
    Activations Density 0.787%

    No Known Activations