© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11938
    Prev
    Next
    INDEX
    Explanations

    the word "gross", and to a lesser extent, words related to genetic material

    oai_token-act-pair · gemini-2.0-flash

    gross

    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
     gross
    -0.74
     Gross
    -0.71
    gross
    -0.68
     GROSS
    -0.67
    Gross
    -0.65
    GROSS
    -0.57
    Arr
    -0.57
    BackPressed
    -0.55
     millas
    -0.55
    tvguidetime
    -0.54
    POSITIVE LOGITS
    <bos>
    1.02
    StoreMessageInfo
    0.64
    DockStyle
    0.61
    IUrlHelper
    0.60
     للمعارف
    0.59
    seamnă
    0.58
    BagLayout
    0.57
    таратура
    0.55
    ttemberg
    0.54
    ultuous
    0.54
    Activations Density 0.546%

    No Known Activations