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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12849
    Prev
    Next
    INDEX
    Explanations

    the word "flower" (and its plural) and related terms

    oai_token-act-pair · gemini-2.0-flash

    flowers

    np_max-act · gemini-2.0-flash

    flowers Method used: 1 — because every max activating token is "flowers"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Majefty
    -1.89
     Monfieur
    -1.86
     myſelf
    -1.80
     itſelf
    -1.80
     Jefus
    -1.73
     Reſ
    -1.65
    ſelf
    -1.64
     pleaſure
    -1.63
     ſeveral
    -1.63
     themſelves
    -1.63
    POSITIVE LOGITS
    ))),
    0.88
    ']").
    0.80
    </i>
    0.80
    '],
    0.77
    '))
    0.76
    '),
    0.76
    ']),
    0.76
    ')],
    0.75
    ')),
    0.75
    '))
    
    0.75
    Activations Density 0.799%

    No Known Activations