© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2764
    Prev
    Next
    INDEX
    Explanations

    language related to printed materials

    oai_token-act-pair · gemini-2.0-flash

    printed materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Muro
    -0.50
     schild
    -0.50
     gela
    -0.48
     متعلقه
    -0.47
     bancaire
    -0.47
     Kard
    -0.47
     Bettina
    -0.47
    Card
    -0.47
     nacionais
    -0.47
     indépend
    -0.47
    POSITIVE LOGITS
    })();
    0.70
    Bakgrunnsstoff
    0.63
    Izvori
    0.62
    حوالہ
    0.60
    әрмәләр
    0.59
     Combien
    0.56
     bookmarks
    0.54
    webElementGuid
    0.54
    betical
    0.53
    Demografie
    0.53
    Activations Density 2.940%

    No Known Activations