© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10273
    Prev
    Next
    INDEX
    Explanations

    words that are somewhat similar to "or", and also finds some words that start with letters that look similar to or

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    er
    -0.59
    contentLoaded
    -0.53
    ER
    -0.49
    erit
    -0.49
    SequentialGroup
    -0.46
    erli
    -0.45
    amazonaws
    -0.43
    erer
    -0.43
    onNext
    -0.42
     patas
    -0.42
    POSITIVE LOGITS
    RTSC
    0.64
     TextAppearance
    0.63
    PreferredItem
    0.60
    最快更新
    0.58
     الرياضيه
    0.57
    BufferException
    0.57
    AndEndTag
    0.57
    r
    0.56
    cticut
    0.54
    LookAnd
    0.53
    Activations Density 1.542%

    No Known Activations