© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15162
    Prev
    Next
    INDEX
    Explanations

    conjunctions, prepositions and time references

    oai_token-act-pair · gemini-2.0-flash

    Website excerpts/details

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    <bos>
    -0.61
    }');
    -0.60
    '}),
    -0.52
     houſe
    -0.51
    ',
    
    
    -0.48
     ſta
    -0.48
    )");
    
    -0.48
    }';
    -0.48
     iſt
    -0.47
    )');
    -0.47
    POSITIVE LOGITS
    chism
    0.55
    toMatchSnapshot
    0.51
    WithMany
    0.49
    																							
    0.48
    																											
    0.46
    ykite
    0.45
    																												
    0.43
    ByExample
    0.43
    cookieParser
    0.43
    asantry
    0.42
    Activations Density 6.257%

    No Known Activations