© 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. 12549
    Prev
    Next
    INDEX
    Explanations

    uses of the words "I", "you", "we", "would", "will", and "to"

    oai_token-act-pair · gemini-2.0-flash

    unique or unusual words

    np_token-act-pair-logits · gpt-4o-mini

    blog post context

    np_max-act-logits · gemini-2.0-flash
    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
    ^(@)
    -0.67
    ]:
    
    -0.66
    ">:
    -0.66
    })();
    
    -0.64
    ++]=
    -0.63
     Theſe
    -0.63
     Jefus
    -0.63
    "):
    
    -0.62
     Waray
    -0.62
    Przeczytaj
    -0.61
    POSITIVE LOGITS
     Administrativna
    0.57
    AddField
    0.47
    ירות
    0.44
     ou
    0.42
     pelan
    0.41
    SpringRunner
    0.41
    middelen
    0.41
    曖昧さ回避
    0.40
     <<<<<<<<<<<<<<
    0.40
     post
    0.40
    Activations Density 1.706%

    No Known Activations