© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15205
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup

    oai_token-act-pair · gemini-2.0-flash

    Scientific publication source 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Roskov
    -0.90
     betweenstory
    -0.87
    AddHtmlAttribute
    -0.81
    featureID
    -0.78
     DBNull
    -0.77
    AsUp
    -0.73
    jface
    -0.72
     CGA
    -0.70
     Numerade
    -0.70
     CGPA
    -0.69
    POSITIVE LOGITS
    dyr
    0.54
    bal
    0.42
     δε
    0.41
    श्न
    0.41
     las
    0.40
    atto
    0.40
    dys
    0.40
    alan
    0.39
     vett
    0.39
    Ђ
    0.39
    Activations Density 4.415%

    No Known Activations