© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10893
    Prev
    Next
    INDEX
    Explanations

    code related to logging in, including the words "login", "email", and "password"

    oai_token-act-pair · gemini-2.0-flash

    login

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     login
    -0.65
    login
    -0.62
     Login
    -0.59
    Login
    -0.59
     “
    -0.54
     count
    -0.53
    SignIn
    -0.51
    登录
    -0.51
     SignIn
    -0.47
    pu
    -0.46
    POSITIVE LOGITS
    StoryboardSegue
    0.93
    sizeCache
    0.89
    PerformLayout
    0.88
    WriteBarrier
    0.85
     betweenstory
    0.83
     Roskov
    0.83
     zelve
    0.81
     Baillargeon
    0.79
    تقاوى
    0.78
     faſt
    0.77
    Activations Density 3.176%

    No Known Activations