© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14289
    Prev
    Next
    INDEX
    Explanations

    references to parents, children, and families

    oai_token-act-pair · gemini-2.0-flash

    parent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     em
    -0.87
     par
    -0.83
     cu
    -0.83
     der
    -0.82
     im
    -0.80
     un
    -0.80
     a
    -0.80
     real
    -0.79
     tem
    -0.78
     sur
    -0.78
    POSITIVE LOGITS
     Monfieur
    1.55
     Theſe
    1.41
     Jefus
    1.41
     anún
    1.40
     fermés
    1.37
     avoient
    1.36
     Cæsar
    1.35
     purpoſe
    1.34
     myſelf
    1.34
     himſelf
    1.31
    Activations Density 3.947%

    No Known Activations