© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4511
    Prev
    Next
    INDEX
    Explanations

    the word "usage" and, with lower activation, the word "performance"

    oai_token-act-pair · gemini-2.0-flash

    usage

    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
     the
    -0.68
     as
    -0.64
     at
    -0.63
    one
    -0.59
     to
    -0.59
    ali
    -0.58
    oo
    -0.57
    usi
    -0.57
     an
    -0.57
     in
    -0.57
    POSITIVE LOGITS
     Efq
    1.13
    NUMX
    1.01
     pleaſure
    0.99
     myſelf
    0.98
     BoxDecoration
    0.98
     doubtnut
    0.95
    
    0.94
     purpoſe
    0.92
     ſtate
    0.92
     itſelf
    0.90
    Activations Density 0.704%

    No Known Activations