© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5033
    Prev
    Next
    INDEX
    Explanations

    the word "left," as well as related words like "right" and "side."

    oai_token-act-pair · gemini-2.0-flash

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ännu
    -0.60
    iestety
    -0.60
    <bos>
    -0.58
    InjectMocks
    -0.58
     berdua
    -0.57
     endnu
    -0.56
    umlu
    -0.56
     részt
    -0.56
    Occurrences
    -0.54
     perciò
    -0.54
    POSITIVE LOGITS
    WebElementEntity
    0.83
    :✨
    0.75
    Carriera
    0.73
    rinfo
    0.72
    GEBURTSDATUM
    0.71
    oneg
    0.70
    Hochspringen
    0.69
     CreateTagHelper
    0.68
    matchCondition
    0.67
     basics
    0.66
    Activations Density 1.163%

    No Known Activations