© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14597
    Prev
    Next
    INDEX
    Explanations

    code and snippets of Lithuanian text

    oai_token-act-pair · 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
    PreferredItem
    -0.78
     kaynağından
    -0.75
    MigrationBuilder
    -0.74
    Портал
    -0.73
    NameInMap
    -0.72
     autorytatywna
    -0.70
     للمعارف
    -0.69
    tagHelperRunner
    -0.69
    featureID
    -0.68
    uolo
    -0.67
    POSITIVE LOGITS
     pride
    0.38
     uttry
    0.37
    grimas
    0.36
     Placement
    0.36
     placement
    0.35
     dima
    0.35
     çe
    0.34
    tesi
    0.33
     beden
    0.33
    下一
    0.33
    Activations Density 0.536%

    No Known Activations