© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14124
    Prev
    Next
    INDEX
    Explanations

    French text discussing computers, particularly the use of terminals for internet access

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash

    French function words

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Drapeau
    -0.59
     désolés
    -0.59
    Scénario
    -0.59
     متعلقه
    -0.57
     Direkt
    -0.56
    ########.
    -0.56
     stinks
    -0.54
     Commencez
    -0.54
     المعيارى
    -0.53
     dus
    -0.53
    POSITIVE LOGITS
     dalamnya
    0.75
    何况
    0.66
    djangoproject
    0.65
    jazdu
    0.65
     nascita
    0.65
     dentelle
    0.65
     magát
    0.65
     ſever
    0.63
    беріга
    0.62
     Jefus
    0.62
    Activations Density 0.264%

    No Known Activations