© 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. 8385
    Prev
    Next
    INDEX
    Explanations

    language regarding financial transactions and prison commissary requests

    oai_token-act-pair · gemini-2.0-flash

    card

    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
    SourceChecksum
    -0.73
     незавершена
    -0.60
     صوتيه
    -0.60
    -------------</
    -0.59
    lgari
    -0.58
    Története
    -0.56
     Référence
    -0.55
    ագրություններ
    -0.54
    stateProvider
    -0.53
     ویکی‌آمباردا
    -0.52
    POSITIVE LOGITS
     card
    0.66
     cards
    0.63
     Card
    0.63
     reload
    0.61
     gift
    0.60
     Reload
    0.58
     recharge
    0.58
    card
    0.58
     Recharge
    0.57
    Card
    0.55
    Activations Density 0.354%

    No Known Activations