© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13979
    Prev
    Next
    INDEX
    Explanations

    words ending in "ization", also sometimes activating on words ending in "ing" or words that might have to do with comfort

    oai_token-act-pair · gemini-2.0-flash

    suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    __(/*!
    -0.91
    исленность
    -0.88
     snippetHide
    -0.88
    Personensuche
    -0.85
    AndEndTag
    -0.85
    ⓧ
    -0.83
    WithIOException
    -0.83
     surla
    -0.80
     transfieras
    -0.77
     TestBed
    -0.75
    POSITIVE LOGITS
    <bos>
    0.64
    bundet
    0.52
     basah
    0.51
     The
    0.49
     felb
    0.48
     hű
    0.48
     giù
    0.46
     vétérina
    0.46
     coffre
    0.46
     educativas
    0.46
    Activations Density 1.066%

    No Known Activations