© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10897
    Prev
    Next
    INDEX
    Explanations

    words such as "of", "the", "to", "a", "in", "my", and "for" that tend to serve as parts of speech (articles, prepositions, etc)

    oai_token-act-pair · gemini-2.0-flash

    punctuation and formal terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    !")
    
    -1.07
    });*/
    -1.06
    .")
    
    -1.01
    ".
    
    -0.96
    ſelves
    -0.96
    .",
    
    -0.94
    ^(@)
    -0.92
     ་་
    -0.90
    .";
    
    -0.89
    })*/
    -0.89
    POSITIVE LOGITS
    ,
    0.57
    .
    0.52
     متعلقه
    0.51
     mattino
    0.50
    \{\\
    0.50
    hilangan
    0.49
     refusé
    0.47
     hiér
    0.46
     démocr
    0.46
    ViewFeatures
    0.44
    Activations Density 24.044%

    No Known Activations