© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12953
    Prev
    Next
    INDEX
    Explanations

    mentions of "lose" and brand names, particularly "Apple"

    oai_token-act-pair · gemini-2.0-flash

    lose

    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
     “
    -0.76
     "");
    
    -0.75
    "]);
    
    -0.71
    "])
    
    -0.69
     
    -0.68
    []);
    -0.68
    ")));
    
    -0.64
     }</
    -0.61
    (");
    -0.60
    '))
    
    -0.60
    POSITIVE LOGITS
     Feminine
    0.91
     quarries
    0.89
     Ephe
    0.88
     sinuses
    0.87
    +#+#
    0.86
     Perse
    0.83
     Nectar
    0.81
     Impala
    0.80
     Jit
    0.79
     morphe
    0.78
    Activations Density 1.926%

    No Known Activations