© 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. 9460
    Prev
    Next
    INDEX
    Explanations

    technical and scientific language, including specifics like measurements, materials, and processes

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     defaultstate
    -0.87
    liptic
    -0.66
    nvarchar
    -0.66
    Билгалдахарш
    -0.63
    piram
    -0.63
    #![
    -0.62
     CURIAM
    -0.59
     AttributeSet
    -0.57
     JSTOR
    -0.57
    insee
    -0.54
    POSITIVE LOGITS
     poveznice
    0.60
     scolas
    0.56
     sottile
    0.55
     domésticos
    0.55
     flesta
    0.54
     înal
    0.53
     extremos
    0.52
    égard
    0.52
     commerciales
    0.52
     définiti
    0.52
    Activations Density 38.727%

    No Known Activations