© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16137
    Prev
    Next
    INDEX
    Explanations

    the word "territory"

    oai_token-act-pair · gemini-2.0-flash

    territory

    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
     itſelf
    -1.09
     Houſe
    -1.03
     Efq
    -0.99
     myſelf
    -0.96
    !")
    -0.95
    "}>
    -0.94
     ―――――
    -0.94
     Monfieur
    -0.93
    ]='\
    -0.92
     Diſ
    -0.91
    POSITIVE LOGITS
     I
    0.66
    ↵
    0.60
     besos
    0.60
    Same
    0.56
     arrivo
    0.55
     S
    0.55
    S
    0.55
    same
    0.54
     pago
    0.53
    Canceled
    0.53
    Activations Density 0.838%

    No Known Activations