© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5719
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions

    oai_token-act-pair · gemini-2.0-flash

    Media and code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.70
    glBegin
    -0.69
    DOCTYPE
    -0.69
    :✨
    -0.68
     autorytatywna
    -0.68
     gyhoeddwyd
    -0.66
     InputDecoration
    -0.65
     &___
    -0.65
    Collegamenti
    -0.65
     мәкал
    -0.62
    POSITIVE LOGITS
    sego
    0.47
    CONCLUSIONS
    0.46
    MigrationBuilder
    0.43
    MathML
    0.40
    tama
    0.40
     لينك
    0.40
    elemField
    0.40
    سع
    0.39
    鉛
    0.39
     jsPsych
    0.39
    Activations Density 0.494%

    No Known Activations