© 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. 14458
    Prev
    Next
    INDEX
    Explanations

    words that are related to photography and its history

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · 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
     Италијани
    -0.82
     مشين
    -0.80
     utafitiHapana
    -0.70
     Italijani
    -0.69
     ویکی‌پدی
    -0.66
    يكب
    -0.63
     beginnetje
    -0.63
     Soccerway
    -0.62
    adpleegd
    -0.61
    AsUp
    -0.60
    POSITIVE LOGITS
    rę
    0.52
     voice
    0.46
     plátano
    0.43
    vertre
    0.43
    GraphicsUnit
    0.43
    TestingModule
    0.42
    럼
    0.41
     marito
    0.40
    Mot
    0.40
     kron
    0.40
    Activations Density 1.231%

    No Known Activations