© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3125
    Prev
    Next
    INDEX
    Explanations

    code snippets, and possibly related terms from other languages

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fileSize
    -0.62
    inians
    -0.56
     newVal
    -0.56
    arschu
    -0.56
     énergé
    -0.56
    TotalCount
    -0.55
     citoy
    -0.55
     '+':
    -0.54
    Geplaatst
    -0.53
     onView
    -0.53
    POSITIVE LOGITS
     ID
    0.75
    id
    0.73
     id
    0.72
    Id
    0.67
    ID
    0.66
    ItemLayout
    0.66
     IDs
    0.60
     Id
    0.59
    <bos>
    0.58
     getId
    0.56
    Activations Density 1.615%

    No Known Activations