© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3217
    Prev
    Next
    INDEX
    Explanations

    the substring "Su" followed by some characters

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -2.30
    Su
    -2.28
     su
    -2.02
     SU
    -1.90
    su
    -1.82
    SU
    -1.65
     Suit
    -1.43
    Suit
    -1.38
     suit
    -1.37
    Sur
    -1.32
    POSITIVE LOGITS
    Parcelize
    0.56
    classmethod
    0.53
    TagMode
    0.49
    щин
    0.49
    ksikon
    0.49
     Delphi
    0.47
    \{\\
    0.47
     Affiliations
    0.47
    BindingResult
    0.47
    躇
    0.47
    Activations Density 5.961%

    No Known Activations