© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15281
    Prev
    Next
    INDEX
    Explanations

    the word "float" and variations of it

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'flo'

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    PathVariable
    -0.52
    ftc
    -0.50
    RectangleBorder
    -0.49
     Cliff
    -0.48
    outi
    -0.48
     cref
    -0.48
    ніципалі
    -0.47
    cliffe
    -0.47
    floors
    -0.47
     DES
    -0.47
    POSITIVE LOGITS
     jScrollPane
    0.62
    gameserver
    0.58
     verzorg
    0.56
     propOrder
    0.55
    #+#
    0.52
     mouseY
    0.50
    LookAnd
    0.50
     MaterialApp
    0.50
     cuida
    0.49
     AssemblyProduct
    0.48
    Activations Density 0.543%

    No Known Activations