© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    commas in run-on sentences and long phrases

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    However
    -0.87
     however
    -0.80
     However
    -0.80
     tuttavia
    -0.75
    Yet
    -0.75
    yet
    -0.73
     yet
    -0.73
     cependant
    -0.73
    however
    -0.69
     jednak
    -0.63
    POSITIVE LOGITS
     but
    1.19
     но
    0.85
     sondern
    0.82
    Referanser
    0.81
    protoimpl
    0.77
    addCriterion
    0.71
    thâu
    0.69
    RegistryLite
    0.67
     considérons
    0.65
     αλλά
    0.64
    Activations Density 0.815%

    No Known Activations