© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    mentions of the results of scientific experimentation and medical diagnoses.

    oai_token-act-pair · gemini-2.0-flash

    Research and study descriptions

    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
    Negative Logits
    argout
    -0.96
    GEBURTSDATUM
    -0.90
    LookAnd
    -0.86
    fjspx
    -0.80
    ագրություններ
    -0.79
    CppMethod
    -0.75
    UnusedPrivate
    -0.72
    Autoritní
    -0.72
    Sucesor
    -0.71
     itſelf
    -0.70
    POSITIVE LOGITS
     expansion
    0.57
     full
    0.56
     rapid
    0.52
     no
    0.51
     completa
    0.49
    BindView
    0.48
     complete
    0.48
     an
    0.47
     increased
    0.47
     equilibrio
    0.46
    Activations Density 2.876%

    No Known Activations