© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2804
    Prev
    Next
    INDEX
    Explanations

    computer code and/or file paths

    oai_token-act-pair · gemini-2.0-flash

    Computer code/specifications

    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
     ſtate
    -0.87
     houſe
    -0.86
     ſche
    -0.85
     perfons
    -0.84
     purpoſe
    -0.79
     fubject
    -0.77
     pleaſure
    -0.77
     ſtre
    -0.74
     area
    -0.72
     chart
    -0.72
    POSITIVE LOGITS
     not
    0.57
     diriger
    0.51
     just
    0.49
    rawDesc
    0.48
     no
    0.47
     so
    0.46
     így
    0.46
     now
    0.46
     do
    0.45
     gelukkig
    0.45
    Activations Density 31.923%

    No Known Activations