© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5473
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical and electronic operations

    oai_token-act-pair · gemini-2.0-flash

    code and operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     modernize
    -1.08
     fermés
    -1.00
    MLLoader
    -0.99
     mobilize
    -0.93
     optimize
    -0.91
     modulate
    -0.90
     educate
    -0.89
     devenus
    -0.89
     synthesize
    -0.88
     stabilize
    -0.87
    POSITIVE LOGITS
     ―――――
    1.22
     itſelf
    1.19
     ་་
    1.16
     Diſ
    1.13
     Efq
    1.07
     Houſe
    1.05
     Conſ
    1.04
     Anſ
    1.04
     Reſ
    1.03
     Inſ
    1.02
    Activations Density 4.319%

    No Known Activations