© 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. 9667
    Prev
    Next
    INDEX
    Explanations

    the word "single" and sometimes the words "bold" and "unique"

    oai_token-act-pair · gemini-2.0-flash

    single

    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
     single
    -2.91
    single
    -2.67
    Single
    -2.59
     Single
    -2.53
     SINGLE
    -2.38
    SINGLE
    -2.03
     singles
    -1.89
     Singles
    -1.62
    Singles
    -1.61
    シングル
    -1.59
    POSITIVE LOGITS
    XmlAccessorType
    0.57
    انيف
    0.54
     verbonden
    0.48
    ühl
    0.46
    tiglie
    0.42
    macam
    0.42
    bouncycastle
    0.42
     partecipanti
    0.40
    liothèque
    0.40
     calculées
    0.39
    Activations Density 2.765%

    No Known Activations