© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6261
    Prev
    Next
    INDEX
    Explanations

    place names that are cities in Argentina

    oai_token-act-pair · gemini-2.0-flash

    Argentina/South America related

    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
     يتيمه
    -0.74
     समीक्षाओं
    -0.57
    upassen
    -0.55
    medriver
    -0.54
    DebuggerStep
    -0.53
    auré
    -0.53
     webdriver
    -0.52
     dAtA
    -0.52
    IonicModule
    -0.52
     iprot
    -0.51
    POSITIVE LOGITS
    #
    0.57
     متعلقه
    0.56
     MPS
    0.50
    hopal
    0.48
    AFX
    0.47
    Cryptography
    0.47
    jspb
    0.46
     TPE
    0.45
     ECA
    0.44
     useStyles
    0.44
    Activations Density 0.364%

    No Known Activations