© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9395
    Prev
    Next
    INDEX
    Explanations

    code snippets with casting

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     laiko
    -0.46
    améli
    -0.44
     distância
    -0.43
    ItemBackground
    -0.42
     discovered
    -0.42
     problemen
    -0.42
     problemet
    -0.40
     zařízení
    -0.40
    guntas
    -0.40
     rang
    -0.40
    POSITIVE LOGITS
    IVEREF
    0.83
    addCriterion
    0.81
    Autoritní
    0.79
    HideFlags
    0.79
    Примечания
    0.77
    Datuak
    0.74
    StructEnd
    0.73
    MemoryWarning
    0.72
    matchCondition
    0.71
    AutoScale
    0.71
    Activations Density 2.937%

    No Known Activations