© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6789
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that indicate that one idea is being added to another and also captures complete sentences

    oai_token-act-pair · gemini-2.0-flash

    Capitalized Words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     (
    -0.62
     K
    -0.62
     di
    -0.56
     V
    -0.55
    <eos>
    -0.54
     
    -0.50
        
    -0.50
     —
    -0.49
     l
    -0.49
      
    -0.48
    POSITIVE LOGITS
     Efq
    1.10
     Monfieur
    1.09
     myſelf
    1.06
     Houſe
    1.03
     Theſe
    1.02
     itſelf
    1.02
     Jefus
    1.01
     Shakspeare
    0.98
     ſeveral
    0.96
    ſelves
    0.93
    Activations Density 0.087%

    No Known Activations