© 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. 345
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially JSON-like data structures

    oai_token-act-pair · gemini-2.0-flash

    structured data/code snippets

    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
     itſelf
    -0.75
     themſelves
    -0.70
     himſelf
    -0.65
    _
    -0.64
    '))
    -0.63
    <bos>
    -0.62
     purpoſe
    -0.61
    "])
    -0.61
    ]`
    -0.61
     myſelf
    -0.61
    POSITIVE LOGITS
    SuppressLint
    0.66
     consultato
    0.65
     TestBed
    0.64
    CppMethod
    0.63
    EFIAPI
    0.61
    nonatomic
    0.59
    原始内容存档于
    0.59
    migrationBuilder
    0.57
    CodeAttribute
    0.57
    flashdata
    0.57
    Activations Density 0.607%

    No Known Activations