© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    the word "all", sometimes followed by "the way"

    oai_token-act-pair · gemini-2.0-flash

    all

    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
     all
    -2.73
    all
    -2.13
     ALL
    -1.72
    All
    -1.72
     All
    -1.66
     semua
    -1.45
    ALL
    -1.45
     все
    -1.38
     всех
    -1.32
     všechny
    -1.24
    POSITIVE LOGITS
     دیکھیے
    0.70
    dafx
    0.65
    GEBURTSDATUM
    0.61
    mapreduce
    0.60
    GenerationType
    0.60
    mybatisplus
    0.59
    {}{}
    0.57
    yntaxException
    0.57
    adpleegd
    0.56
    principalColumn
    0.56
    Activations Density 0.581%

    No Known Activations