© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10404
    Prev
    Next
    INDEX
    Explanations

    references to code being printed for javascript

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     <<<<<<<<<<<<<<
    -0.62
     Италијани
    -0.62
     has
    -0.60
    memoized
    -0.56
    期刊论文
    -0.55
    氓
    -0.55
    stdafx
    -0.54
    PhysRevD
    -0.54
     were
    -0.54
    étrie
    -0.54
    POSITIVE LOGITS
     InputDecoration
    0.56
     originalen
    0.55
    NewGuid
    0.54
    CodeAttribute
    0.50
     useState
    0.49
    Бахар
    0.49
     MotionEvent
    0.48
    UnsafeEnabled
    0.48
    ButterKnife
    0.47
    mybatisplus
    0.47
    Activations Density 0.433%

    No Known Activations