© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6013
    Prev
    Next
    INDEX
    Explanations

    the word "role," sometimes in conjunction with words that make it abstract, like energy or medicine

    oai_token-act-pair · gemini-2.0-flash

    role

    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
    ).
    -0.85
     …)
    -0.84
    ".
    -0.80
    
    -0.79
     ་་
    -0.76
    ?
    -0.75
    ).</
    -0.73
    )";
    -0.73
     \\
    -0.72
    Manbalar
    -0.72
    POSITIVE LOGITS
    tuned
    0.66
     démocr
    0.60
     télécharge
    0.60
     supérieurs
    0.60
    shifted
    0.59
    UnitTesting
    0.59
     liquido
    0.58
    Autoritní
    0.58
     ilha
    0.58
    versed
    0.58
    Activations Density 2.879%

    No Known Activations