© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11162
    Prev
    Next
    INDEX
    Explanations

    phrases related to caveats or reservations

    oai_token-act-pair · gemini-2.0-flash

    Problems and challenges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -0.82
     purpoſe
    -0.77
     }{@
    -0.75
     esternos
    -0.74
     pleaſure
    -0.74
     reaſon
    -0.73
     nahilalakip
    -0.72
    ſelf
    -0.71
     ſte
    -0.70
     ſtate
    -0.70
    POSITIVE LOGITS
     k
    1.90
    k
    1.29
     K
    1.14
    K
    0.98
     growing
    0.94
     Growing
    0.87
    ks
    0.86
    Growing
    0.80
    growing
    0.76
     n
    0.74
    Activations Density 1.803%

    No Known Activations