© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13065
    Prev
    Next
    INDEX
    Explanations

    a specific Japanese surname

    oai_token-act-pair · gemini-2.0-flash

    ts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     or
    -0.51
    IBUS
    -0.48
     civile
    -0.48
     keting
    -0.47
     omission
    -0.46
    Malley
    -0.46
    комнат
    -0.46
     omitted
    -0.46
    ague
    -0.46
     pro
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.98
     itſelf
    0.91
     myſelf
    0.78
     متعلقه
    0.78
    Lähteet
    0.78
     Monfieur
    0.77
    StructEnd
    0.77
    Portail
    0.76
     referenties
    0.75
     resourceCulture
    0.75
    Activations Density 0.859%

    No Known Activations