© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3619
    Prev
    Next
    INDEX
    Explanations

    the prefix 'sub' within words

    oai_token-act-pair · gemini-2.0-flash

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sub
    -2.81
    Sub
    -2.56
     Sub
    -2.55
    sub
    -2.55
    SUB
    -2.14
     SUB
    -2.03
     subs
    -1.83
    サブ
    -1.73
    getSub
    -1.72
     getSub
    -1.69
    POSITIVE LOGITS
    ReusableCell
    0.52
    dau
    0.52
    ArgsConstructor
    0.50
    heira
    0.46
    rien
    0.45
    wahlen
    0.45
    ParseTree
    0.44
     feu
    0.43
    AxisAlignment
    0.43
    баты
    0.42
    Activations Density 0.395%

    No Known Activations