© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3206
    Prev
    Next
    INDEX
    Explanations

    scientific or technical language, especially units, rates, and mathematical terms, alongside statistical data

    oai_token-act-pair · gemini-2.0-flash

    Physics and calculations

    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
    RenderAtEndOf
    -0.69
     kasarigan
    -0.51
     senjata
    -0.49
     colgantes
    -0.47
     sanitarias
    -0.47
     teatro
    -0.46
     Turquía
    -0.46
     wholeheartedly
    -0.46
     artesanales
    -0.46
     fábricas
    -0.45
    POSITIVE LOGITS
     diameters
    0.63
     تضيفلها
    0.60
     diameter
    0.57
    neſs
    0.55
    istoitu
    0.52
    DrawerToggle
    0.52
    jspx
    0.52
    licity
    0.51
    ſelf
    0.50
    sivity
    0.50
    Activations Density 11.613%

    No Known Activations