© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14594
    Prev
    Next
    INDEX
    Explanations

    discussions about illegal activities, accusations, and legal proceedings in Brazil.

    oai_token-act-pair · gemini-2.0-flash

    describing scandal and corruption

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    }}/>
    -0.57
    ண
    -0.52
    ั่ว
    -0.50
     Demet
    -0.49
     Salat
    -0.48
    icu
    -0.48
    ngrx
    -0.48
    ]];
    -0.47
    DataSet
    -0.47
     تضيفلها
    -0.47
    POSITIVE LOGITS
    PointerException
    0.58
     بتاريخ
    0.54
    AndEndTag
    0.53
     defaultstate
    0.53
    ACJA
    0.52
     setuptools
    0.52
    ValueStyle
    0.51
    клопе
    0.51
    toHaveBeenCalled
    0.51
    CppCodeGen
    0.50
    Activations Density 0.636%

    No Known Activations