© 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. 15056
    Prev
    Next
    INDEX
    Explanations

    words beginning with the letters "int" or "ex" that are often part of medical or legal terminology

    oai_token-act-pair · gemini-2.0-flash

    Int

    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
    DataMember
    -0.49
     hObject
    -0.48
    +#+#
    -0.48
     Czy
    -0.47
     Çe
    -0.47
     raiſ
    -0.47
     Voiture
    -0.46
     MONO
    -0.46
    جهة
    -0.46
     Gees
    -0.46
    POSITIVE LOGITS
     defaultstate
    0.72
    ensed
    0.63
    iction
    0.59
     propOrder
    0.57
     autorytatywna
    0.57
    ridor
    0.57
    adah
    0.56
    urismo
    0.54
    endance
    0.54
    ropriate
    0.54
    Activations Density 10.704%

    No Known Activations