© 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. 3448
    Prev
    Next
    INDEX
    Explanations

    the verb "was" and forms of the verb "is."

    oai_token-act-pair · gemini-2.0-flash

    was

    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
     introduction
    -0.70
    messageInfo
    -0.69
     introduces
    -0.65
     发表于
    -0.64
    INTRODU
    -0.63
     Introduced
    -0.61
    createTextNode
    -0.60
    createClass
    -0.59
    новниш
    -0.59
     introducing
    -0.59
    POSITIVE LOGITS
     sådan
    0.56
     policiales
    0.54
    ositol
    0.52
     africains
    0.52
     guerres
    0.50
    lichem
    0.49
    AndEndTag
    0.48
     cérami
    0.48
     LOGGER
    0.48
     européennes
    0.47
    Activations Density 7.504%

    No Known Activations