© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4124
    Prev
    Next
    INDEX
    Explanations

    mentions of things or locations being large or spectacular

    oai_token-act-pair · gemini-2.0-flash

    largest/biggest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    
    -0.83
     مشين
    -0.64
     PhpStorm
    -0.62
    AnimationsModule
    -0.62
    étit
    -0.57
    BeginInit
    -0.57
    ГЛА
    -0.56
    tagHelperRunner
    -0.55
    addContainerGap
    -0.55
    ANTLR
    -0.54
    POSITIVE LOGITS
     chang
    0.52
    ioon
    0.49
     tá
    0.47
    peq
    0.46
    )](
    0.46
     незавершена
    0.44
    ิด
    0.44
    orney
    0.43
    样子
    0.43
    ppure
    0.43
    Activations Density 6.828%

    No Known Activations