© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4886
    Prev
    Next
    INDEX
    Explanations

    topics that appear in recipes or technical documentation, that have some parts in numbered lists or bullet points

    oai_token-act-pair · gemini-2.0-flash

    food

    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
     Majefty
    -1.73
     ―――――
    -1.71
     myſelf
    -1.66
     ་་
    -1.65
     Efq
    -1.63
    ſelf
    -1.63
    ſelves
    -1.59
     Monfieur
    -1.56
     itſelf
    -1.56
     pleaſure
    -1.54
    POSITIVE LOGITS
    -
    0.16
     egna
    0.16
    （
    0.14
      
    0.13
    –
    0.13
     bords
    0.13
     (
    0.13
     ejes
    0.12
    ↵↵
    0.12
     
    0.12
    Activations Density 17.626%

    No Known Activations