© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    US state names and words that often appear near them like "Department" or "National"

    oai_token-act-pair · gemini-2.0-flash

    US states and government

    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
     متعلقه
    -0.80
     saites
    -0.75
     المعيارى
    -0.73
    AddTagHelper
    -0.69
    Diwedd
    -0.67
    Datuak
    -0.65
    بوابة
    -0.65
     snippetHide
    -0.63
    adaptiveStyles
    -0.62
     Meksiku
    -0.62
    POSITIVE LOGITS
    ptest
    0.53
     Wallflower
    0.44
    jScrollPane
    0.42
    Còn
    0.41
    lwjgl
    0.41
    cestershire
    0.41
     secteur
    0.41
     Refugees
    0.40
    assar
    0.40
     péné
    0.40
    Activations Density 4.683%

    No Known Activations