© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13154
    Prev
    Next
    INDEX
    Explanations

    a mix of capitalized abbreviations, names, and other capitalized words or word fragments of 2-3 characters

    oai_token-act-pair · gemini-2.0-flash

    Titles and abbreviations

    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
    theless
    -0.89
    withstanding
    -0.80
    poptosis
    -0.77
    Tikang
    -0.77
    IUrlHelper
    -0.76
    queous
    -0.73
    itudinal
    -0.68
    logical
    -0.68
     تكبرها
    -0.66
    ortic
    -0.65
    POSITIVE LOGITS
     industriels
    0.71
     enfans
    0.66
     armées
    0.63
     chrétiens
    0.63
     chimiques
    0.61
     juridiques
    0.61
     élas
    0.60
     militaires
    0.60
     guerras
    0.59
     efficaces
    0.59
    Activations Density 10.404%

    No Known Activations