© 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. 14737
    Prev
    Next
    INDEX
    Explanations

    the word "city", especially those in the United States

    oai_token-act-pair · gemini-2.0-flash

    City

    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
     purpoſe
    -1.24
     ſtate
    -1.19
     myſelf
    -1.16
     Houſe
    -1.12
     ſche
    -1.11
     Majefty
    -1.11
     ſever
    -1.10
     Reſ
    -1.09
     feroit
    -1.07
     Diſ
    -1.06
    POSITIVE LOGITS
     the
    0.94
    ↵↵
    0.90
     The
    0.74
    '
    0.70
     
    0.64
     "
    0.63
    ↵
    0.62
    <eos>
    0.60
     of
    0.59
    the
    0.59
    Activations Density 0.871%

    No Known Activations