© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1929
    Prev
    Next
    INDEX
    Explanations

    legal jargon and court documents.

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ReusableCell
    -0.75
     فريبيس
    -0.75
    ]--;
    -0.69
    Predecesor
    -0.62
    RegressionTest
    -0.61
    NameInMap
    -0.61
    PerformLayout
    -0.58
    mtrl
    -0.58
    GraphicsUnit
    -0.57
     незавершена
    -0.56
    POSITIVE LOGITS
     at
    3.23
     At
    1.91
    At
    1.89
    at
    1.69
     tại
    1.50
     AT
    1.06
     atx
    0.96
     ats
    0.93
     	e
    0.92
    앳
    0.90
    Activations Density 9.445%

    No Known Activations