© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11628
    Prev
    Next
    INDEX
    Explanations

    the word "password"

    oai_token-act-pair · gemini-2.0-flash

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     password
    -1.67
    Password
    -1.62
    password
    -1.58
     Password
    -1.45
     passwords
    -1.18
    PASSWORD
    -1.09
     PASSWORD
    -1.07
    密码
    -1.00
     contraseña
    -0.89
    パスワード
    -0.87
    POSITIVE LOGITS
     Мексичка
    0.86
    WebServlet
    0.84
    
    0.83
     AttributeSet
    0.75
    MLLoader
    0.73
    PhysRevLett
    0.69
    ImageContext
    0.67
    twimg
    0.66
    ohs
    0.65
    fatto
    0.65
    Activations Density 0.270%

    No Known Activations