© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14114
    Prev
    Next
    INDEX
    Explanations

    articles with technical language and mathematical symbols in the science and engineering fields

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     a
    -0.86
     an
    -0.72
     the
    -0.49
     to
    -0.48
    ,
    -0.47
     any
    -0.47
     (
    -0.44
     Z
    -0.43
     in
    -0.42
     cortes
    -0.42
    POSITIVE LOGITS
    awtextra
    1.21
     myſelf
    0.88
     Anſ
    0.87
     purpoſe
    0.87
    DeleteBehavior
    0.86
     Jefus
    0.86
     Efq
    0.85
     themſelves
    0.85
    ValueStyle
    0.83
     Administrativna
    0.83
    Activations Density 9.968%

    No Known Activations