© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    the word "floor"

    oai_token-act-pair · gemini-2.0-flash

    floor

    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
     floor
    -3.19
     Floor
    -2.80
    floor
    -2.70
    Floor
    -2.67
     FLOOR
    -2.47
    FLOOR
    -2.22
     floors
    -2.17
     Floors
    -1.74
     flooring
    -1.60
    floors
    -1.59
    POSITIVE LOGITS
    okości
    0.66
    💼
    0.55
    ContextHolder
    0.52
    AndEndTag
    0.52
    ();)
    0.51
    />";
    0.50
    reus
    0.49
    횟
    0.47
    Viited
    0.47
     تضيفلها
    0.46
    Activations Density 0.742%

    No Known Activations