© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5678
    Prev
    Next
    INDEX
    Explanations

    names of academic journals

    oai_token-act-pair · gemini-2.0-flash

    academic and research papers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    neté
    -0.55
     Exhibits
    -0.50
    ועל
    -0.48
     Khur
    -0.47
    лизм
    -0.47
     exhibits
    -0.47
     clearest
    -0.47
    
    -0.46
    Abp
    -0.45
     voyez
    -0.45
    POSITIVE LOGITS
    ResumeLayout
    0.72
     ModelExpression
    0.68
    webElementXpaths
    0.66
    .*")]
    0.65
     GenerationType
    0.63
    SuppressMessage
    0.59
     mapStateToProps
    0.59
    Зноскі
    0.58
     joaat
    0.57
    httphttps
    0.56
    Activations Density 0.163%

    No Known Activations