© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1077
    Prev
    Next
    INDEX
    Explanations

    the name "John"

    oai_token-act-pair · gemini-2.0-flash

    John

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    jsxFileName
    -0.81
    GEBURTSDATUM
    -0.73
    Попис
    -0.70
    encodeWith
    -0.69
     esternos
    -0.68
    UnsafeEnabled
    -0.68
    |')
    -0.66
     Roskov
    -0.66
     '{@
    -0.65
     ViewController
    -0.64
    POSITIVE LOGITS
    μαστε
    0.43
     Nevis
    0.41
     Middlesbrough
    0.40
    ztat
    0.39
    kül
    0.39
     Derby
    0.38
    zyści
    0.36
     MSM
    0.36
     Bullets
    0.35
     Mémoires
    0.35
    Activations Density 0.804%

    No Known Activations