© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11688
    Prev
    Next
    INDEX
    Explanations

    references to singing

    oai_token-act-pair · gemini-2.0-flash

    sing

    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
     $_"
    -1.73
     itſelf
    -1.59
    ^(@)
    -1.59
    ſelf
    -1.52
     becauſe
    -1.47
     Theſe
    -1.45
     Efq
    -1.44
     myſelf
    -1.41
     themſelves
    -1.38
    ſelves
    -1.38
    POSITIVE LOGITS
    <eos>
    1.02
        
    0.92
      
    0.89
    0.88
    ↵↵
    0.88
     The
    0.87
    _
    0.86
       
    0.85
    .
    0.85
    ↵
    0.84
    Activations Density 1.514%

    No Known Activations