© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2007
    Prev
    Next
    INDEX
    Explanations

    words that are followed by the word "as"

    oai_token-act-pair · gemini-2.0-flash

    variations of "too" or "as well"

    np_token-act-pair-logits · gpt-4o-mini

    also, too

    np_max-act-logits · gemini-2.0-flash
    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
    ModelAdmin
    -0.57
     snippetHide
    -0.57
    balleur
    -0.51
    setopt
    -0.51
     المعيارى
    -0.50
     للمعارف
    -0.48
    gouv
    -0.47
    oplayer
    -0.46
    gidas
    -0.46
    યા
    -0.45
    POSITIVE LOGITS
     too
    1.80
     aswell
    1.78
    too
    1.41
     TOO
    1.22
     Too
    1.20
    Too
    1.20
     well
    1.14
     sowie
    1.09
    sowie
    1.04
     así
    1.01
    Activations Density 4.233%

    No Known Activations