© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12684
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the ability or need to do something

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    duma
    -0.55
    fromnode
    -0.54
    MENAFN
    -0.54
    Халык
    -0.54
    gnato
    -0.54
     considérons
    -0.54
    onDestroy
    -0.54
    setUserId
    -0.52
    adaptiveStyles
    -0.51
    extAlignment
    -0.51
    POSITIVE LOGITS
    get
    0.65
    try
    0.64
    marry
    0.62
    hold
    0.62
    raise
    0.61
    find
    0.60
    accumulate
    0.59
    synthesize
    0.58
    sell
    0.57
    argue
    0.57
    Activations Density 15.430%

    No Known Activations