© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11968
    Prev
    Next
    INDEX
    Explanations

    the word 'too'

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

    instances of the word "too" and words that intensify or modify the meaning of nearby words.

    oai_token-act-pair · gemini-2.0-flash

    intensity or degree

    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
     funnier
    -0.57
    spaceBetween
    -0.56
     socialization
    -0.56
     wiser
    -0.55
     aidant
    -0.54
     Geophysical
    -0.54
    ContentLoaded
    -0.54
    llary
    -0.54
    richTextPanel
    -0.54
     purer
    -0.54
    POSITIVE LOGITS
    Jîn
    0.69
    ConstraintMaker
    0.60
     carefully
    0.53
    sever
    0.50
     often
    0.49
    béco
    0.47
     frequently
    0.46
    (!__
    0.46
     sering
    0.46
     strongly
    0.46
    Activations Density 2.738%

    No Known Activations