© 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. 16352
    Prev
    Next
    INDEX
    Explanations

    references to a specific place called Edo State

    oai_token-act-pair · gemini-2.0-flash

    State

    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
     propOrder
    -1.14
     Efq
    -0.98
     Monfieur
    -0.85
     auffi
    -0.84
    Hentet
    -0.84
     فريبيس
    -0.82
    IntoConstraints
    -0.81
    berdayakan
    -0.81
     initComponents
    -0.80
     ContentValues
    -0.80
    POSITIVE LOGITS
    THISDAY
    1.02
     Nigerian
    0.91
     Nigerians
    0.86
     Nigeria
    0.81
    asanjo
    0.79
     naira
    0.78
    Nigerian
    0.76
     Abuja
    0.76
    Nigeria
    0.75
    lorin
    0.75
    Activations Density 1.290%

    No Known Activations