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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5511
    Prev
    Next
    INDEX
    Explanations

    negative statements, difficulties, and political commentary

    oai_token-act-pair · gemini-2.0-flash

    unexpected characters or patterns

    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
     myſelf
    -1.03
     poffe
    -1.02
     Jefus
    -0.98
     Monfieur
    -0.98
     Efq
    -0.95
     ſtate
    -0.94
     himſelf
    -0.93
     themſelves
    -0.91
     ſeveral
    -0.90
     auffi
    -0.89
    POSITIVE LOGITS
     pur
    0.51
    ix
    0.49
    id
    0.48
    Â
    0.48
     consultato
    0.47
    php
    0.47
     
    0.46
    /**
    0.46
    rs
    0.45
    ↵
    0.45
    Activations Density 0.415%

    No Known Activations