© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_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
     x
    -0.85
     p
    -0.67
     t
    -0.65
     i
    -0.63
     v
    -0.62
    x
    -0.61
     s
    -0.60
     item
    -0.59
     X
    -0.57
     d
    -0.57
    POSITIVE LOGITS
     itſelf
    0.92
     poffible
    0.91
     Efq
    0.90
     myſelf
    0.88
     photolibrary
    0.88
     Monfieur
    0.88
     purpoſe
    0.83
     Egli
    0.83
     Shakspeare
    0.83
    Personensuche
    0.83
    Activations Density 0.713%

    No Known Activations