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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 945
    Prev
    Next
    INDEX
    Explanations

    words or phrases that would serve as a title or heading for something

    oai_token-act-pair · gemini-2.0-flash

    formal language/conclusions

    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
    Of
    -0.71
     Of
    -0.57
    is
    -0.57
    in
    -0.54
    da
    -0.54
    es
    -0.53
    And
    -0.53
    it
    -0.52
    ir
    -0.52
    ida
    -0.52
    POSITIVE LOGITS
    +:+
    0.90
     Theſe
    0.80
     vectorielles
    0.76
     vectorielle
    0.72
     ainfi
    0.71
     Monfieur
    0.71
     plufieurs
    0.70
     prisonniers
    0.69
     feroit
    0.69
     protoimpl
    0.69
    Activations Density 1.781%

    No Known Activations