© 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. 12277
    Prev
    Next
    INDEX
    Explanations

    instances of the word "which", often followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    which

    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
     which
    -2.16
    which
    -1.67
     WHICH
    -1.39
     Which
    -1.31
    Which
    -1.25
     laquelle
    -1.16
     lequel
    -0.96
    hich
    -0.90
     vilket
    -0.89
     cual
    -0.87
    POSITIVE LOGITS
    expandindo
    0.71
    dafx
    0.65
    anyahu
    0.57
     autorytatywna
    0.57
     hamilton
    0.56
     ::=
    0.55
     Chriftian
    0.55
    cyj
    0.55
     quartzite
    0.54
     /^\
    0.52
    Activations Density 1.267%

    No Known Activations