© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10357
    Prev
    Next
    INDEX
    Explanations

    code snippets, questions in Q&A format, and copyright notices

    oai_token-act-pair · gemini-2.0-flash

    Non-English/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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     mead
    -0.49
     PCV
    -0.49
    /*-
    -0.48
    ptonshire
    -0.48
     TextAppearance
    -0.48
     warp
    -0.47
    minate
    -0.47
     SwitchCompat
    -0.47
     $<$
    -0.47
     Hars
    -0.47
    POSITIVE LOGITS
     препратки
    0.73
     invokingState
    0.67
     @
    0.61
     saites
    0.59
     démocr
    0.56
     Мексичка
    0.56
     tombé
    0.56
     mourut
    0.56
    SWIG
    0.53
    ьаж
    0.53
    Activations Density 2.588%

    No Known Activations