© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12520
    Prev
    Next
    INDEX
    Explanations

    first person plural pronouns and related references to shared experience

    oai_token-act-pair · gemini-2.0-flash

    restaurant and travel reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    uxxxx
    -0.58
    ChildScrollView
    -0.58
    BarStyle
    -0.56
    ाहरण
    -0.50
    styleType
    -0.50
    napp
    -0.49
    ContentAsync
    -0.49
    entiment
    -0.48
    MIG
    -0.48
    werd
    -0.47
    POSITIVE LOGITS
     Autorizaciones
    0.66
     CreateTagHelper
    0.64
    utilisons
    0.59
     passés
    0.57
    BeginContext
    0.56
     bandou
    0.54
    ंदीखरीदारी
    0.52
    Espèce
    0.52
     progesterone
    0.50
    DataAnnotations
    0.49
    Activations Density 11.840%

    No Known Activations