© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as assignment operators, booleans, and function names

    oai_token-act-pair · gemini-2.0-flash

    =

    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
    onomía
    -0.64
     Steg
    -0.63
    addCriterion
    -0.63
     gekomen
    -0.57
    出版年
    -0.56
    betic
    -0.56
     meantime
    -0.56
     propOrder
    -0.55
     الرياضيه
    -0.54
    )))));
    -0.54
    POSITIVE LOGITS
    CURLOPT
    0.72
    findpost
    0.59
     CURLOPT
    0.57
    oprot
    0.56
    PageRoute
    0.54
    ervlak
    0.54
    ########.
    0.53
    الإنجليزية
    0.52
    TestBed
    0.52
    forName
    0.52
    Activations Density 11.899%

    No Known Activations