© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9627
    Prev
    Next
    INDEX
    Explanations

    mentions of Italian food or things related to Italy

    oai_token-act-pair · gemini-2.0-flash

    italian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Italian
    -1.54
     Italy
    -1.40
    Italian
    -1.30
     italian
    -1.19
    Italy
    -1.18
     Italians
    -1.16
     italiano
    -1.08
     Italia
    -1.06
     italiana
    -1.05
     ITAL
    -1.04
    POSITIVE LOGITS
     الحره
    0.82
     للاسماء
    0.77
    ⓧ
    0.70
     通販
    0.68
    ">//
    0.67
     betweenstory
    0.65
    +:+
    0.64
    #+#
    0.63
    GIH
    0.63
     WALTZ
    0.63
    Activations Density 1.052%

    No Known Activations