© 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. 10029
    Prev
    Next
    INDEX
    Explanations

    abstract nouns ending in "-ity", "-ship", "-ness", "-ism", "-ence", "-ance", "-tion", "-tics", and other words related to the arts and philosophy

    oai_token-act-pair · gemini-2.0-flash

    Art

    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
     enfans
    -0.96
     avoient
    -0.96
     étoient
    -0.89
     feroit
    -0.87
     quæ
    -0.84
     Cæsar
    -0.82
     uſed
    -0.81
     Chriftian
    -0.81
     dieß
    -0.80
     fubject
    -0.79
    POSITIVE LOGITS
     ProtoMessage
    0.87
     الحره
    0.84
    aarrggbb
    0.74
    endphp
    0.73
    yntaxException
    0.72
     للاسماء
    0.70
     MonoBehaviour
    0.69
    fjspx
    0.68
    interopRequire
    0.65
    httphttps
    0.64
    Activations Density 3.695%

    No Known Activations