© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14070
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Facebook accounts and SMS messages, often in a non-English language (likely Croatian).

    oai_token-act-pair · gemini-2.0-flash

    Software code and international characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    engeti
    -0.48
    StoryboardSegue
    -0.47
     potuto
    -0.47
     biểu
    -0.40
     rimasto
    -0.40
    ūt
    -0.40
    Tē
    -0.39
     next
    -0.39
    bruch
    -0.38
    Leistung
    -0.38
    POSITIVE LOGITS
    IntoConstraints
    0.71
    MessageTagHelper
    0.66
    Personensuche
    0.66
    yship
    0.62
    transQ
    0.62
    OGND
    0.60
    glLoadIdentity
    0.60
    ledning
    0.59
     EClass
    0.58
    verwijspagina
    0.57
    Activations Density 0.616%

    No Known Activations