© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3783
    Prev
    Next
    INDEX
    Explanations

    the phrases "name of" in a variety of contexts, including categories and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     name
    -1.27
     Name
    -1.11
    name
    -1.05
     names
    -1.05
     title
    -1.00
    Name
    -0.97
     Namen
    -0.94
    名字
    -0.93
     NAME
    -0.91
     Names
    -0.90
    POSITIVE LOGITS
     $_"
    0.84
    TypedDataSet
    0.82
     Jefus
    0.79
    featureID
    0.77
     Efq
    0.77
     myſelf
    0.76
    __*/
    0.75
    ])).
    0.74
    }")
    0.72
     itſelf
    0.71
    Activations Density 1.219%

    No Known Activations