© 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. 14993
    Prev
    Next
    INDEX
    Explanations

    the word "thoughts"

    oai_token-act-pair · gemini-2.0-flash

    thoughts

    np_max-act · gemini-2.0-flash

    thoughts

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     programme
    -0.79
     program
    -0.73
    MemoryWarning
    -0.72
    الحياه
    -0.63
    WebKit
    -0.63
    goku
    -0.62
    toPromise
    -0.61
    OkHttpClient
    -0.60
    Enllaces
    -0.59
    Билгалдахарш
    -0.58
    POSITIVE LOGITS
     pitié
    1.01
     devenus
    0.85
     nôtre
    0.83
     automatiques
    0.81
     normaux
    0.80
     auroit
    0.80
     refusé
    0.79
     devriez
    0.79
     survie
    0.78
     enfans
    0.78
    Activations Density 1.018%

    No Known Activations