© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5857
    Prev
    Next
    INDEX
    Explanations

    Java import statements

    oai_token-act-pair · gemini-2.0-flash

    reflect

    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
     myſelf
    -1.61
     itſelf
    -1.57
    UnusedPrivate
    -1.46
     Reſ
    -1.44
    ſelf
    -1.43
     themſelves
    -1.40
     Efq
    -1.38
     pleaſure
    -1.37
     whoſe
    -1.36
     ་་
    -1.35
    POSITIVE LOGITS
    ,
    0.83
     
    0.71
     ...
    0.71
     the
    0.69
     I
    0.68
     to
    0.66
     in
    0.65
     "
    0.64
    ...
    0.64
     of
    0.63
    Activations Density 1.280%

    No Known Activations