© 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. 4441
    Prev
    Next
    INDEX
    Explanations

    technical documents about engineering

    oai_token-act-pair · gemini-2.0-flash

    moving earth

    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
     Concrete
    -0.68
    Concrete
    -0.68
     Cement
    -0.66
     CONCRETE
    -0.65
    concrete
    -0.62
    writeFieldEnd
    -0.62
    tonsoft
    -0.59
     concrete
    -0.59
     beton
    -0.59
     cement
    -0.57
    POSITIVE LOGITS
     ExecuteAsync
    0.61
    MENAFN
    0.56
     fill
    0.53
     plages
    0.52
    +:+
    0.52
     betweenstory
    0.51
     Шта
    0.50
    fill
    0.50
    assigns
    0.50
     pulseras
    0.50
    Activations Density 2.855%

    No Known Activations