© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11241
    Prev
    Next
    INDEX
    Explanations

    the end of sentences and paragraphs, various punctuation marks, and some interjections.

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     soon
    -0.88
     Soon
    -0.70
    soon
    -0.67
     shortly
    -0.65
     quickly
    -0.65
    Soon
    -0.64
     '\\;'
    -0.60
     slowly
    -0.57
     gradually
    -0.56
     fearing
    -0.55
    POSITIVE LOGITS
     Савезне
    0.78
    AccessorTable
    0.77
    ագրություններ
    0.67
     transfieras
    0.64
     kaarangay
    0.62
    //
    0.60
     resourceCulture
    0.59
    +#+#
    0.57
     femininos
    0.57
     stället
    0.57
    Activations Density 6.879%

    No Known Activations