© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8267
    Prev
    Next
    INDEX
    Explanations

    language that is used to sell real estate

    oai_token-act-pair · gemini-2.0-flash

    Sentence fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     فريبيس
    -0.54
    TypedDataSet
    -0.53
    исленность
    -0.52
     vong
    -0.51
    amazonaws
    -0.51
    ratto
    -0.49
    ]--;
    -0.48
    estacks
    -0.48
    teca
    -0.47
    escal
    -0.47
    POSITIVE LOGITS
     مشين
    0.58
    mphony
    0.58
     chemins
    0.57
     članak
    0.57
    帖最后由
    0.56
    rfloor
    0.54
    Slf
    0.53
    uitton
    0.53
     purchase
    0.52
    Purchase
    0.52
    Activations Density 19.387%

    No Known Activations