© 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. 9810
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms, especially the word "login"

    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_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
     protoimpl
    -0.99
    GraphicsUnit
    -0.99
     useAppContext
    -0.90
    DebuggerNonUser
    -0.90
    NewUrlParser
    -0.90
     BorderRadius
    -0.88
    存于互联网档案馆
    -0.88
    LookAnd
    -0.82
    #![
    -0.82
    printStackTrace
    -0.82
    POSITIVE LOGITS
    s
    0.79
    ه
    0.65
    ISMO
    0.62
    اً
    0.61
    يين
    0.59
    wiegend
    0.58
     Mayer
    0.57
    ی
    0.57
    ovo
    0.57
    displaystyle
    0.57
    Activations Density 1.251%

    No Known Activations