© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12733
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data processing, compression, and control

    oai_token-act-pair · gemini-2.0-flash

    compression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Ter
    -0.63
     rend
    -0.55
    <bos>
    -0.52
    Ter
    -0.51
    ero
    -0.51
    以
    -0.51
     ter
    -0.51
    '
    -0.49
    hl
    -0.48
     att
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.92
     مرئيه
    0.84
    ArgsConstructor
    0.83
    InputBorder
    0.82
     MainAxisSize
    0.80
     itſelf
    0.80
     مشين
    0.77
    ſelf
    0.76
     HasFactory
    0.73
    setupUi
    0.73
    Activations Density 3.974%

    No Known Activations